BestHub
Sign in
Tagged articles
658 articles
Page 6 of 7
DataFunTalk
DataFunTalk
Feb 20, 2023 · Artificial Intelligence

ChatGPT Technology, Localization Efforts, and Open‑Source Large Models – Overview and Practices

This article presents an overview of ChatGPT technology, its evolution, current challenges, a three‑stage learning process, data organization and evaluation, details of domestic localization efforts, practical solutions, and the release of a Chinese open‑source large model with training guidance.

ChatGPTModel Localizationdata annotation
0 likes · 12 min read
ChatGPT Technology, Localization Efforts, and Open‑Source Large Models – Overview and Practices
Architect
Architect
Feb 19, 2023 · Artificial Intelligence

Training a Positive Review Generator with RLHF and PPO

This article demonstrates how to apply Reinforcement Learning from Human Feedback (RLHF) using a sentiment‑analysis model as a reward function and Proximal Policy Optimization (PPO) to fine‑tune a language model that generates positive product reviews, complete with code snippets and experimental results.

Language ModelPPORLHF
0 likes · 10 min read
Training a Positive Review Generator with RLHF and PPO
dbaplus Community
dbaplus Community
Feb 18, 2023 · Artificial Intelligence

Why ChatGPT Still Gets It Wrong: Inside RLHF and Model Consistency

ChatGPT, OpenAI’s latest language model, builds on GPT‑3 but uses supervised fine‑tuning and Reinforcement Learning from Human Feedback (RLHF) to improve alignment, yet its training methods still cause consistency issues such as invalid help, hallucinations, bias, and limited explainability.

ChatGPTModel AlignmentPPO
0 likes · 17 min read
Why ChatGPT Still Gets It Wrong: Inside RLHF and Model Consistency
Open Source Linux
Open Source Linux
Feb 13, 2023 · Artificial Intelligence

How Does ChatGPT Work? Inside RLHF and Model Consistency

This article explains the inner workings of ChatGPT, detailing its evolution from GPT‑3, the role of reinforcement learning from human feedback (RLHF) in improving consistency, the training pipeline steps, and the limitations and evaluation methods of large language models.

AIChatGPTModel Alignment
0 likes · 15 min read
How Does ChatGPT Work? Inside RLHF and Model Consistency
Kuaishou Tech
Kuaishou Tech
Feb 10, 2023 · Artificial Intelligence

Seven Kuaishou Papers Accepted at WWW 2023 on Reinforcement Learning and Recommendation Systems

On January 25, Kuaishou’s community science team announced that seven of its papers were accepted at the ACM Web Conference 2023 (WWW’23), covering reinforcement‑learning‑based user retention, constrained actor‑critic recommendation, divide‑and‑conquer embedding retrieval, causal embedding with contrastive learning, latent action space exploration, dual‑interest factorization attention, and multi‑task reinforcement learning for recommendation.

AIKuaishouWWW 2023
0 likes · 17 min read
Seven Kuaishou Papers Accepted at WWW 2023 on Reinforcement Learning and Recommendation Systems
Top Architect
Top Architect
Feb 9, 2023 · Artificial Intelligence

How ChatGPT Works: Training, RLHF, and Consistency Issues

ChatGPT, OpenAI’s latest language model, builds on GPT‑3 and improves performance through supervised fine‑tuning, human‑feedback reinforcement learning (RLHF), and PPO optimization, addressing consistency challenges such as misaligned outputs, bias, and hallucinations while evaluating helpfulness, truthfulness, and harmlessness.

ChatGPTModel AlignmentRLHF
0 likes · 15 min read
How ChatGPT Works: Training, RLHF, and Consistency Issues
DataFunSummit
DataFunSummit
Feb 8, 2023 · Artificial Intelligence

Technical Architecture and Training Process of ChatGPT

ChatGPT, a dialogue-focused language model, builds on the GPT family and employs techniques such as Reinforcement Learning from Human Feedback (RLHF), the TAMER framework, and a three-stage training pipeline (supervised fine‑tuning, reward modeling, and PPO reinforcement learning) to achieve advanced conversational capabilities.

ChatGPTGPTLanguage Model
0 likes · 7 min read
Technical Architecture and Training Process of ChatGPT
Architects' Tech Alliance
Architects' Tech Alliance
Feb 7, 2023 · Artificial Intelligence

ChatGPT: Technical Principles, Architecture, and the Role of Human‑Feedback Reinforcement Learning

This article explains how ChatGPT builds on GPT‑3 with improved accuracy and coherence, details its training pipeline that combines supervised fine‑tuning and Reinforcement Learning from Human Feedback (RLHF), discusses consistency challenges, evaluation metrics, and the limitations of the RLHF approach.

AI AlignmentChatGPTPPO
0 likes · 15 min read
ChatGPT: Technical Principles, Architecture, and the Role of Human‑Feedback Reinforcement Learning
Model Perspective
Model Perspective
Jan 12, 2023 · Artificial Intelligence

Neural Networks Explained: Architecture, Training, and Reinforcement Basics

This article introduces neural networks, covering their layered structure, common types like CNNs and RNNs, key components such as activation functions, loss, learning rate, backpropagation, dropout, batch normalization, and extends to reinforcement learning concepts including MDPs, policies, value functions, and Q‑learning.

CNNNeural NetworksRNN
0 likes · 6 min read
Neural Networks Explained: Architecture, Training, and Reinforcement Basics
DataFunTalk
DataFunTalk
Dec 30, 2022 · Artificial Intelligence

Graph Representation Learning for Drug Package Recommendation: Discriminative and Generative Approaches

This article reviews the challenges of drug package recommendation in smart healthcare and presents two graph‑based solutions—a discriminative model (DPR) that scores existing drug packages and a generative model (DPG) that creates personalized packages—demonstrating superior performance through extensive experiments and analysis.

AI in healthcareGenerative Modelsdrug recommendation
0 likes · 19 min read
Graph Representation Learning for Drug Package Recommendation: Discriminative and Generative Approaches
Alimama Tech
Alimama Tech
Dec 28, 2022 · Artificial Intelligence

Sustainable Online Reinforcement Learning for Auto-bidding (SORL)

The Sustainable Online Reinforcement Learning (SORL) framework tackles offline inconsistency in auto‑bidding by iteratively gathering safe online data from real ad systems with a Lipschitz‑based exploration method and training a variance‑suppressed conservative Q‑learning policy, achieving safer, more stable, and higher‑performing bids on Alibaba’s platform.

auto-biddingoffline inconsistencyonline advertising
0 likes · 18 min read
Sustainable Online Reinforcement Learning for Auto-bidding (SORL)
Architecture Digest
Architecture Digest
Dec 15, 2022 · Artificial Intelligence

Technical Overview of ChatGPT: Training Pipeline, RLHF, and Its Potential to Replace Search Engines

This article explains ChatGPT's underlying technology—including its three‑stage training pipeline with supervised fine‑tuning, reward‑model learning, and reinforcement learning from human feedback—while analyzing whether the model can realistically replace traditional search engines such as Google or Baidu.

AIChatGPTRLHF
0 likes · 15 min read
Technical Overview of ChatGPT: Training Pipeline, RLHF, and Its Potential to Replace Search Engines
IT Architects Alliance
IT Architects Alliance
Dec 13, 2022 · Artificial Intelligence

Technical Principles and Training Process of ChatGPT

The article explains ChatGPT’s underlying technology, detailing its three-stage training pipeline—supervised fine‑tuning, reward‑model learning, and reinforcement learning with PPO—while discussing its strengths, limitations, and potential integration with traditional search engines.

AIChatGPTLLM
0 likes · 14 min read
Technical Principles and Training Process of ChatGPT
Tencent Cloud Developer
Tencent Cloud Developer
Dec 9, 2022 · Artificial Intelligence

An Overview of ChatGPT: Technology, Training Process, and Applications

The article outlines ChatGPT’s conversational capabilities, its InstructGPT‑based architecture, a three‑stage RLHF training pipeline involving supervised fine‑tuning, human‑ranked response generation, and PPO optimization, and discusses its strengths, limitations, diverse applications, and future directions for multimodal, up‑to‑date assistants.

AI applicationsChatGPTPPO
0 likes · 18 min read
An Overview of ChatGPT: Technology, Training Process, and Applications
Architect's Guide
Architect's Guide
Dec 9, 2022 · Artificial Intelligence

Technical Principles and Training Process of ChatGPT

The article explains how ChatGPT builds on the GPT‑3.5 large language model, using human‑annotated data and Reinforcement Learning from Human Feedback (RLHF) across three training stages to improve instruction understanding, answer quality, and continual model enhancement, while also discussing its potential to complement or replace traditional search engines.

AIChatGPTInstruction Tuning
0 likes · 15 min read
Technical Principles and Training Process of ChatGPT
IT Architects Alliance
IT Architects Alliance
Dec 8, 2022 · Artificial Intelligence

Technical Principles and Training Process of ChatGPT

This article explains the technical foundations of ChatGPT, detailing its three-stage training pipeline—supervised fine‑tuning with human‑annotated data, reward model training via pairwise ranking, and reinforcement learning from human feedback—while also discussing its limitations compared to traditional search engines and potential future enhancements.

AIChatGPTRLHF
0 likes · 14 min read
Technical Principles and Training Process of ChatGPT
vivo Internet Technology
vivo Internet Technology
Dec 7, 2022 · Artificial Intelligence

Mixing Heterogeneous Queues in Vivo's Information Flow and App Store: Challenges, Practices, and RL/Deep Learning Solutions

Vivo tackles the complex problem of mixing heterogeneous content queues—ads, games, and organic items—in its information‑flow and app‑store by evolving from rule‑based weighting to Q‑learning and deep‑learning position models that respect product constraints, preserve ordering, and balance short‑term revenue with long‑term user experience, while planning deeper personalization and on‑device solutions.

AdvertisingApp StoreDeep Learning
0 likes · 14 min read
Mixing Heterogeneous Queues in Vivo's Information Flow and App Store: Challenges, Practices, and RL/Deep Learning Solutions
Top Architect
Top Architect
Dec 7, 2022 · Artificial Intelligence

Technical Principles of ChatGPT and Its Prospects for Replacing Traditional Search Engines

The article explains how ChatGPT builds on GPT‑3.5 with supervised fine‑tuning, reward‑model training and reinforcement learning from human feedback, analyzes why it cannot yet replace search engines due to hallucinations, knowledge freshness and cost, and proposes a hybrid architecture that combines LLM generation with traditional retrieval to overcome these limitations.

AIChatGPTRLHF
0 likes · 16 min read
Technical Principles of ChatGPT and Its Prospects for Replacing Traditional Search Engines
HomeTech
HomeTech
Nov 16, 2022 · Artificial Intelligence

Fundamentals and Policy Gradient Algorithms in Reinforcement Learning with Applications to Scene Text Recognition

This article introduces the basic concepts of reinforcement learning, derives model‑based and model‑free policy gradient methods—including vanilla policy gradient and Actor‑Critic—explains their mathematical foundations, and demonstrates their use in scene text recognition and image captioning tasks.

AIAttention Mechanismactor-critic
0 likes · 22 min read
Fundamentals and Policy Gradient Algorithms in Reinforcement Learning with Applications to Scene Text Recognition
AntTech
AntTech
Nov 7, 2022 · Blockchain

Effectively Generating Vulnerable Transaction Sequences in Smart Contracts with Reinforcement Learning‑Guided Fuzzing

This paper presents a reinforcement‑learning‑based fuzzer (RLF) that generates transaction sequences likely to trigger smart‑contract vulnerabilities, combining vulnerability‑driven and coverage‑driven rewards to improve detection efficiency and outperform existing state‑of‑the‑art tools.

RL-based fuzzerreinforcement learning
0 likes · 12 min read
Effectively Generating Vulnerable Transaction Sequences in Smart Contracts with Reinforcement Learning‑Guided Fuzzing
NetEase LeiHuo Testing Center
NetEase LeiHuo Testing Center
Nov 4, 2022 · Artificial Intelligence

Applying AI for Game Balance Testing: DNN Victory Prediction and Genetic Algorithm Optimization

This article details a practical AI-driven workflow for a turn‑based card game, covering problem background, data modeling with a DNN victory‑prediction network, reinforcement‑learning‑based data generation, and a genetic‑algorithm search to identify the strongest and weakest team compositions.

AIDNNGame Balance
0 likes · 18 min read
Applying AI for Game Balance Testing: DNN Victory Prediction and Genetic Algorithm Optimization
DataFunTalk
DataFunTalk
Nov 4, 2022 · Artificial Intelligence

Explainable Knowledge Graph Reasoning: Background, Advances, Motivation, Recent Research, and Outlook

This article reviews explainable knowledge graph reasoning, covering its background, core concepts, downstream applications, major reasoning methods, motivations for interpretability, recent advances such as hierarchical and Bayesian reinforcement learning, meta‑path mining, and future research directions.

Knowledge Graphexplainable AIgraph reasoning
0 likes · 18 min read
Explainable Knowledge Graph Reasoning: Background, Advances, Motivation, Recent Research, and Outlook
Youku Technology
Youku Technology
Oct 28, 2022 · Artificial Intelligence

Enlarging Long‑time Dependencies via Reinforcement‑Learning‑Based Memory Network for Movie Affective Analysis

The authors introduce a reinforcement‑learning‑driven memory network that augments long‑range dependencies for continuous valence‑arousal emotion prediction in movies, integrating five multimodal features and a DDPG‑based update policy, which yields state‑of‑the‑art performance across multiple affective‑analysis and summarization benchmarks.

VA affect modellong‑term dependenciesmemory network
0 likes · 16 min read
Enlarging Long‑time Dependencies via Reinforcement‑Learning‑Based Memory Network for Movie Affective Analysis
Model Perspective
Model Perspective
Oct 26, 2022 · Artificial Intelligence

Master Machine Learning Algorithms: Types, Python Code & Real-World Examples

This article categorizes machine learning algorithms into supervised, unsupervised, and reinforcement learning, then details ten common algorithms—including linear regression, logistic regression, decision trees, SVM, Naive Bayes, K‑NN, K‑means, random forest, and dimensionality reduction—accompanied by clear Python code examples and illustrative diagrams.

AlgorithmsPythonUnsupervised Learning
0 likes · 14 min read
Master Machine Learning Algorithms: Types, Python Code & Real-World Examples
Sohu Tech Products
Sohu Tech Products
Oct 12, 2022 · Artificial Intelligence

AlphaTensor: DeepMind’s AI System for Discovering Faster Matrix Multiplication Algorithms

DeepMind’s AlphaTensor, built on AlphaZero and reinforcement learning, automatically discovers novel, provably correct matrix multiplication algorithms that outperform classic methods like Strassen’s, demonstrating how modern AI can automate algorithm discovery and significantly accelerate computations across many fields.

AIAlphaTensorDeepMind
0 likes · 8 min read
AlphaTensor: DeepMind’s AI System for Discovering Faster Matrix Multiplication Algorithms
Alimama Tech
Alimama Tech
Sep 21, 2022 · Artificial Intelligence

Alibaba's Three Papers Accepted at NeurIPS 2022

Alibaba’s research team secured three NeurIPS 2022 papers—introducing an Adaptive Parameter Generation network that boosts click‑through rates and revenue, a tuning‑free Global Batch Gradient Aggregation method that speeds recommendation model training by 2.4×, and a Sustainable Online Reinforcement Learning framework that outperforms existing auto‑bidding strategies.

NeurIPSRecommendation Systemsgradient aggregation
0 likes · 6 min read
Alibaba's Three Papers Accepted at NeurIPS 2022
GuanYuan Data Tech Team
GuanYuan Data Tech Team
Sep 8, 2022 · Artificial Intelligence

How AI Reinforcement Learning Transforms Smart Replenishment in Retail

This article examines the technical challenges of intelligent replenishment—model stability, complexity, generalization, and interpretability—and explains how a few‑shot imitation learning and inverse reinforcement learning framework can overcome these issues to deliver reliable, low‑cost AI‑driven supply‑chain decisions.

AISupply Chainimitation learning
0 likes · 22 min read
How AI Reinforcement Learning Transforms Smart Replenishment in Retail
Alimama Tech
Alimama Tech
Sep 7, 2022 · Artificial Intelligence

Curriculum-Guided Bayesian Reinforcement Learning for ROI-Constrained Real-Time Bidding

The paper presents a Curriculum‑Guided Bayesian Reinforcement Learning (CBRL) framework that models ROI‑constrained real‑time bidding as a partially observable constrained MDP, using hard‑margin indicator rewards and a curriculum of relaxed proxy problems to achieve fast, constraint‑satisfying, Bayes‑optimal policies that outperform existing methods on large‑scale industrial data.

Bayesian RLMDPROI constraint
0 likes · 15 min read
Curriculum-Guided Bayesian Reinforcement Learning for ROI-Constrained Real-Time Bidding
Bilibili Tech
Bilibili Tech
Aug 30, 2022 · Artificial Intelligence

Neural MMO Massive AI Team Survival Challenge: Advances in Multi‑Agent Decision AI

The IJCAI‑2022 Neural MMO Massive AI Team Survival Challenge demonstrated that deep reinforcement‑learning agents can achieve sophisticated cooperation and competition among 128 agents in a large‑scale MMO‑style world, highlighting the growing focus on decision‑AI, the effectiveness of self‑play and CTDE, and the platform’s potential for future research into population‑level behavior, economics, and complex real‑world decision making.

AI competitionDecision AIMassive AI
0 likes · 11 min read
Neural MMO Massive AI Team Survival Challenge: Advances in Multi‑Agent Decision AI
Bilibili Tech
Bilibili Tech
Aug 30, 2022 · Artificial Intelligence

Reinforcement Learning in Neural MMO: Background, Environment, Competition Solution, and Insights

The article reviews reinforcement learning applied to Neural MMO—a large‑scale, multi‑agent MMO environment—detailing its competitive IJCAI 2022 track, the winning LastOrder solution with transformer‑CNN‑LSTM architecture, reward shaping, a Fictitious Self‑Play meta‑solver, and Bilibili’s scalable Newton training framework.

AI in GamesDistributed TrainingMeta Solver
0 likes · 9 min read
Reinforcement Learning in Neural MMO: Background, Environment, Competition Solution, and Insights
Laiye Technology Team
Laiye Technology Team
Aug 29, 2022 · Artificial Intelligence

Evolution of Dialogue Management: From Rule‑Based to Data‑Driven Systems and Industrial Deployments

This article reviews the historical development of dialogue management—from early rule‑based and finite‑state approaches to modern data‑driven and reinforcement‑learning methods—and examines how major industry platforms such as Amazon Alexa, Amazon Lex, and RASA implement these techniques in practice.

Amazon AlexaData-drivenNLU
0 likes · 16 min read
Evolution of Dialogue Management: From Rule‑Based to Data‑Driven Systems and Industrial Deployments
IEG Growth Platform Technology Team
IEG Growth Platform Technology Team
Aug 16, 2022 · Artificial Intelligence

Actor‑Critic Reinforcement Learning for Real‑Time Bidding in Mobile Game Advertising

The paper proposes an actor‑critic reinforcement‑learning model (ACRL) that leverages PPO and a deep structured semantic model to optimize real‑time bidding strategies for mobile game ads under CPM and budget constraints, addressing long user lifecycles and sparse conversion data while demonstrably improving ROI in both offline simulations and online A/B tests.

ROIactor-criticmobile advertising
0 likes · 16 min read
Actor‑Critic Reinforcement Learning for Real‑Time Bidding in Mobile Game Advertising
IEG Growth Platform Technology Team
IEG Growth Platform Technology Team
Aug 10, 2022 · Artificial Intelligence

Two Tencent IEG Papers Accepted at CIKM: Actor‑Critic Reinforcement Learning for Optimal Bidding and Adversarial Adaptation for Cross‑Domain Recommendation

Tencent's IEG Growth Middle Platform team announced that two of its research papers—one presenting an actor‑critic reinforcement learning model for real‑time bidding in online display advertising and the other proposing an adversarial adaptation framework for cross‑domain recommendation—were accepted at the top‑tier CIKM conference, highlighting novel algorithms that achieve state‑of‑the‑art performance and have been deployed to serve billions of daily impressions.

Advertisingadversarial adaptationcross-domain recommendation
0 likes · 4 min read
Two Tencent IEG Papers Accepted at CIKM: Actor‑Critic Reinforcement Learning for Optimal Bidding and Adversarial Adaptation for Cross‑Domain Recommendation
Model Perspective
Model Perspective
Aug 5, 2022 · Artificial Intelligence

What Are the Essential Steps and Types of Machine Learning?

Machine learning involves five core steps—from data collection and preparation to model training, evaluation, and improvement—while encompassing supervised, unsupervised, and reinforcement learning methods, each with distinct algorithms and real-world applications across finance, healthcare, and retail.

ApplicationsUnsupervised Learningmachine learning
0 likes · 7 min read
What Are the Essential Steps and Types of Machine Learning?
NetEase LeiHuo Testing Center
NetEase LeiHuo Testing Center
Jul 29, 2022 · Artificial Intelligence

AI‑Powered Compatibility Testing for Mobile Games: Platform Design, Scene Traversal, and Anomaly Detection

This article describes an AI‑driven mobile game compatibility testing framework that combines a cloud device farm, a Poco‑based scene‑traversal module with reinforcement‑learning click strategies, and a computer‑vision anomaly detection model enhanced by data‑augmentation techniques to identify UI defects across diverse devices and game scenarios.

AIScene Traversalreinforcement learning
0 likes · 14 min read
AI‑Powered Compatibility Testing for Mobile Games: Platform Design, Scene Traversal, and Anomaly Detection
GuanYuan Data Tech Team
GuanYuan Data Tech Team
Jul 28, 2022 · Artificial Intelligence

Unlocking Reinforcement Learning: Core Concepts, Algorithms, and Real‑World Applications

This article introduces reinforcement learning by defining agents, environments, rewards, and policies, explains key concepts such as Markov Decision Processes and Bellman equations, and surveys major algorithms—including dynamic programming, Monte‑Carlo, TD learning, policy gradients, Q‑learning, DQN, and evolution strategies—while highlighting practical challenges and notable case studies like AlphaGo Zero.

Deep LearningEvolution StrategiesMDP
0 likes · 27 min read
Unlocking Reinforcement Learning: Core Concepts, Algorithms, and Real‑World Applications
Youku Technology
Youku Technology
Jul 5, 2022 · Artificial Intelligence

Enlarging the Long-time Dependencies via RL-based Memory Network in Movie Affective Analysis

The paper introduces a reinforcement‑learning‑driven memory network that stores and updates historical video information via DDPG, overcoming LSTM/Transformer limitations on long‑duration movie sequences, and achieves state‑of‑the‑art affective prediction on LIRIS‑ACCEDE and related datasets, with real‑world deployments in AI content inspection and film‑element knowledge graphs.

long-term dependenciesmemory networkmovie affective analysis
0 likes · 5 min read
Enlarging the Long-time Dependencies via RL-based Memory Network in Movie Affective Analysis
58 Tech
58 Tech
Jun 24, 2022 · Artificial Intelligence

Reinforcement Learning for Lead Generation in Task‑Oriented Dialogue Systems

This article presents a reinforcement‑learning‑based approach to improve lead‑capture efficiency of a task‑oriented chatbot used in local services, detailing the system architecture, RL algorithms (DQN/DDQN), data construction, model training, offline and online evaluation, and the resulting commercial gains.

DQNLead Generationcustomer-service
0 likes · 27 min read
Reinforcement Learning for Lead Generation in Task‑Oriented Dialogue Systems
AntTech
AntTech
Jun 22, 2022 · Cloud Computing

Meta Reinforcement Learning Framework for Predictive Autoscaling in Cloud Environments

This article presents a cloud-native, end‑to‑end autoscaling solution that integrates traffic forecasting, CPU utilization meta‑prediction, and a reinforcement‑learning‑based scaling decision module into a fully differentiable system, achieving higher resource utilization and cost efficiency as demonstrated by ACM SIGKDD 2022 research.

Meta LearningPredictive Modelingautoscaling
0 likes · 10 min read
Meta Reinforcement Learning Framework for Predictive Autoscaling in Cloud Environments
DataFunSummit
DataFunSummit
Jun 21, 2022 · Artificial Intelligence

JiuGe: An Automatic Chinese Classical Poetry Generation System – Algorithms and Research Overview

This article presents the JiuGe system developed by THUNLP for automatically generating Chinese classical poetry, detailing its research motivations, model architecture—including salient‑clue, working‑memory, topic‑memory, style‑transfer and reinforcement‑learning components—implementation, applications, and future directions.

Deep LearningKnowledge GraphPoetry Generation
0 likes · 18 min read
JiuGe: An Automatic Chinese Classical Poetry Generation System – Algorithms and Research Overview
Huawei Cloud Developer Alliance
Huawei Cloud Developer Alliance
Jun 1, 2022 · Artificial Intelligence

How AI Beats Super Mario with PPO in 5 Minutes

This tutorial demonstrates how to use Huawei Cloud ModelArts and the Proximal Policy Optimization (PPO) reinforcement‑learning algorithm to train an AI agent that can clear most Super Mario levels within about 1500 episodes, even for users with no coding experience.

AIModelArtsPPO
0 likes · 6 min read
How AI Beats Super Mario with PPO in 5 Minutes
Meituan Technology Team
Meituan Technology Team
Apr 28, 2022 · Artificial Intelligence

Multi-Action Computation Allocation via Evolutionary Strategies in Meituan Takeaway Advertising

This article analyzes Meituan's delivery advertising system, detailing the shift from linear programming to an evolutionary‑strategy‑based multi‑action allocation (ES‑MACA), describing problem formalization, offline training, reward evaluation, online decision flow, extensive offline and online experiments, and future directions toward reinforcement learning.

AdvertisingMeituanevolutionary strategies
0 likes · 28 min read
Multi-Action Computation Allocation via Evolutionary Strategies in Meituan Takeaway Advertising
Code DAO
Code DAO
Apr 28, 2022 · Artificial Intelligence

Model-Based Reinforcement Learning from Raw Video: A Detailed Walkthrough

The article explains how to train robots to learn tasks directly from raw video using model-based reinforcement learning, covering POMDP formulation, CNN auto‑encoders, latent‑space representations, iLQR optimization, and a step‑by‑step pipeline with concrete examples and references.

CNN autoencoderPOMDPRobotics
0 likes · 11 min read
Model-Based Reinforcement Learning from Raw Video: A Detailed Walkthrough
Code DAO
Code DAO
Apr 24, 2022 · Artificial Intelligence

How Transfer Learning Accelerates Deep Learning Across Vision, NLP, and Reinforcement Learning

The article explains how transfer learning reduces data and time requirements in deep learning by reusing pretrained models for vision, natural language processing, and reinforcement learning, while discussing challenges such as overfitting, the need for progressive networks, entropy regularization, domain adaptation, multi‑task learning, and model distillation.

Deep Learningdomain adaptationmodel distillation
0 likes · 10 min read
How Transfer Learning Accelerates Deep Learning Across Vision, NLP, and Reinforcement Learning
DaTaobao Tech
DaTaobao Tech
Apr 13, 2022 · Artificial Intelligence

Machine‑Learning Based Bandwidth Prediction and Adaptive Streaming for Taobao Live: Concerto, OnRL, and Loki

Alibaba’s Taobao Live team replaced rule‑based bandwidth estimators with three machine‑learning solutions—Concerto, OnRL, and Loki—trained on over a million hours of global live‑stream data, achieving up to 13% throughput gain, threefold stall reduction, and up to 44% lower 95th‑percentile stalls, now deployed commercially.

Real-time Videoadaptive bitratebandwidth prediction
0 likes · 14 min read
Machine‑Learning Based Bandwidth Prediction and Adaptive Streaming for Taobao Live: Concerto, OnRL, and Loki
Alimama Tech
Alimama Tech
Mar 16, 2022 · Artificial Intelligence

Deep GSP: Multi‑Objective Deep Learning Based Advertising Auction Mechanism

Deep GSP is a multi‑objective, deep‑learning ad auction that jointly learns rank scores while enforcing game‑theoretic constraints—monotonicity, incentive compatibility, and Nash equilibrium—and a smooth‑transition penalty, using DDPG reinforcement learning to outperform traditional GSP across revenue, clicks, conversions, and add‑to‑cart metrics.

advertising auctionmechanism designmulti-objective optimization
0 likes · 18 min read
Deep GSP: Multi‑Objective Deep Learning Based Advertising Auction Mechanism
DataFunSummit
DataFunSummit
Mar 12, 2022 · Artificial Intelligence

Evolution of Re‑ranking Techniques in Kuaishou Short‑Video Recommendation System

This article details Kuaishou's short‑video recommendation pipeline, explaining the challenges of large‑scale sequencing, the development of sequence re‑ranking, multi‑content mixing, on‑device re‑ranking, and reinforcement‑learning‑based strategies, and demonstrates how these innovations improve user engagement and business metrics.

KuaishouRecommendation Systemsmulti-content mixing
0 likes · 15 min read
Evolution of Re‑ranking Techniques in Kuaishou Short‑Video Recommendation System
DataFunSummit
DataFunSummit
Mar 3, 2022 · Artificial Intelligence

Sequence Optimization, Context-Aware CTR Re-Estimation, and Session-Level Auction for JD Advertising Ranking

The article presents JD's technical evolution for advertising ranking, covering technology selection for recommendation ad sorting, context‑aware CTR re‑estimation, reinforcement‑learning‑based sequence optimization, and a session‑level auction mechanism that together improve monetization efficiency and long‑term user value.

CTRauctionreinforcement learning
0 likes · 18 min read
Sequence Optimization, Context-Aware CTR Re-Estimation, and Session-Level Auction for JD Advertising Ranking
DataFunTalk
DataFunTalk
Feb 24, 2022 · Artificial Intelligence

Sequence Optimization and Context-Aware CTR Re-Estimation for JD Advertising Ranking

The article presents JD's technical evolution for advertising ranking, covering recommendation ad sorting, context‑aware CTR re‑estimation, reinforcement‑learning‑based sequence optimization, and session‑level auction mechanisms, and includes a Q&A that highlights practical gains and implementation challenges.

AdvertisingCTR predictionContext-Aware
0 likes · 14 min read
Sequence Optimization and Context-Aware CTR Re-Estimation for JD Advertising Ranking
DataFunTalk
DataFunTalk
Feb 20, 2022 · Artificial Intelligence

Distilled Reinforcement Learning Framework for Recommendation (DRL-Rec): Design, Modules, and Experimental Evaluation

This article presents DRL-Rec, a distilled reinforcement learning framework for recommendation that integrates an exploring‑filtering module and confidence‑guided distillation to compress RL‑based recommenders while improving accuracy, and reports significant offline and online performance gains on a large‑scale system.

knowledge distillationonline experimentsreinforcement learning
0 likes · 16 min read
Distilled Reinforcement Learning Framework for Recommendation (DRL-Rec): Design, Modules, and Experimental Evaluation
DataFunTalk
DataFunTalk
Feb 10, 2022 · Artificial Intelligence

Evolution of Re‑ranking Techniques in Kuaishou Short‑Video Recommendation System

This article details the technical evolution of Kuaishou's short‑video recommendation pipeline, focusing on sequence re‑ranking, multi‑content mixing, and on‑device re‑ranking, and explains how transformer‑based models, generator‑evaluator frameworks, and reinforcement‑learning strategies are employed to maximize overall sequence value, user engagement, and revenue.

KuaishouSequence Modelingmulti-content mixing
0 likes · 15 min read
Evolution of Re‑ranking Techniques in Kuaishou Short‑Video Recommendation System
IEG Growth Platform Technology Team
IEG Growth Platform Technology Team
Jan 10, 2022 · Artificial Intelligence

Applying Reinforcement Learning to Optimize Advertising Bidding ROI

This article presents a comprehensive overview of using reinforcement learning to solve advertising bidding ROI optimization, covering historical foundations, methodological reasoning, system architecture, practical implementation details, challenges, evaluation metrics, and recommended algorithms for real‑world ad placement scenarios.

AdvertisingROI optimizationad bidding
0 likes · 17 min read
Applying Reinforcement Learning to Optimize Advertising Bidding ROI
DataFunTalk
DataFunTalk
Jan 3, 2022 · Artificial Intelligence

Top AI Stories of 2021: Large‑Scale Pretrained Models, Transformers, Multimodal AI, and Emerging Challenges

The article reviews the 2021 AI landscape, highlighting the race for ever‑larger pretrained models, the dominance of Transformers across modalities, the promise and limits of large models, the rise of multimodal systems, regulatory considerations, and the still‑nascent progress in reinforcement learning.

AI GovernanceAI industryMultimodal AI
0 likes · 12 min read
Top AI Stories of 2021: Large‑Scale Pretrained Models, Transformers, Multimodal AI, and Emerging Challenges
DataFunSummit
DataFunSummit
Jan 1, 2022 · Artificial Intelligence

Intelligent Advertising Delivery System: Budget‑Constrained Bidding, Multi‑Constraint Bidding, Sequential Allocation, and Multi‑Channel Optimization

This article systematically introduces Alibaba's advertising intelligence platform, covering the evolution from simple CPM/CPC models to advanced budget‑constrained, multi‑constraint, and sequential bidding strategies, multi‑channel optimization, and reinforcement‑learning‑based solutions that jointly maximize advertiser ROI and platform revenue.

Multi‑Channelbudget optimizationmachine learning
0 likes · 34 min read
Intelligent Advertising Delivery System: Budget‑Constrained Bidding, Multi‑Constraint Bidding, Sequential Allocation, and Multi‑Channel Optimization
58 Tech
58 Tech
Dec 28, 2021 · Artificial Intelligence

Reinforcement Learning for Cold‑Start Job Recommendation in 58.com

This talk explains how 58.com tackles the cold‑start and interest‑divergence problems of its massive blue‑collar job recruitment platform by modeling the recommendation process as a reinforcement‑learning task, detailing the use of multi‑armed bandit, contextual bandit, and linear‑UCB algorithms, offline evaluation pipelines, online deployment, and observed performance gains.

Contextual Banditcold startjob recommendation
0 likes · 25 min read
Reinforcement Learning for Cold‑Start Job Recommendation in 58.com
DataFunTalk
DataFunTalk
Dec 17, 2021 · Artificial Intelligence

Applying Reinforcement Learning to Solve Cold‑Start Problems in 58.com Job Recruitment

This talk explains how 58.com’s massive blue‑collar recruitment platform uses reinforcement‑learning techniques—including multi‑armed bandits, contextual MAB, and linear UCB—to address cold‑start and interest‑divergence challenges, describes the system architecture, offline evaluation, online deployment, and reports an 8% uplift in new‑user conversion.

Online Learningcold startcontextual MAB
0 likes · 26 min read
Applying Reinforcement Learning to Solve Cold‑Start Problems in 58.com Job Recruitment
Code DAO
Code DAO
Dec 14, 2021 · Artificial Intelligence

Building a Chess AI from Scratch: Combining AlphaZero and Transformers (Part 2)

This article walks through constructing a learnable chess AI by integrating AlphaZero‑style Monte Carlo Tree Search with a decoder‑only Transformer, detailing the game tree logic, model architecture, input and output encodings, self‑play training loop, and code implementation in PyTorch.

AlphaZeroMonteCarloTreeSearchPyTorch
0 likes · 23 min read
Building a Chess AI from Scratch: Combining AlphaZero and Transformers (Part 2)
IEG Growth Platform Technology Team
IEG Growth Platform Technology Team
Dec 6, 2021 · Artificial Intelligence

Model-Free Reinforcement Learning for ROI Optimization: Methods, Advertising Applications, and Tencent Game Advertising Practice

This article introduces model‑free reinforcement learning fundamentals, reviews mainstream solution methods such as Monte‑Carlo, Temporal‑Difference, and n‑step TD with eligibility traces, discusses their application in online advertising and presents Tencent's game advertising practice, including algorithm choices, reward design, and experimental results.

A3CAdvertisingPPO
0 likes · 17 min read
Model-Free Reinforcement Learning for ROI Optimization: Methods, Advertising Applications, and Tencent Game Advertising Practice
Code DAO
Code DAO
Dec 3, 2021 · Artificial Intelligence

Understanding Actor‑Critic and A2C: From Policy Gradients to REINFORCE in RL

This article derives the policy‑gradient objective for discrete actions, implements the Monte‑Carlo REINFORCE algorithm in PyTorch, explains the actor‑critic framework, introduces Advantage Actor‑Critic (A2C) versus A3C, and demonstrates their performance on the OpenAI Gym CartPole‑v0 environment.

A2COpenAI GymPython
0 likes · 13 min read
Understanding Actor‑Critic and A2C: From Policy Gradients to REINFORCE in RL
Code DAO
Code DAO
Nov 28, 2021 · Artificial Intelligence

Adapting Soft Actor‑Critic for Discrete Action Spaces in Deep Reinforcement Learning

This article explains how to modify the Soft Actor‑Critic (SAC) algorithm—originally designed for continuous actions—to work with discrete action environments, presents the required changes to the actor and critic loss functions, provides a full PyTorch implementation, and evaluates the method on the CartPole‑v1 benchmark.

CartPoleDiscrete ActionsEntropy Regularization
0 likes · 20 min read
Adapting Soft Actor‑Critic for Discrete Action Spaces in Deep Reinforcement Learning
ByteDance Terminal Technology
ByteDance Terminal Technology
Oct 26, 2021 · Mobile Development

Fastbot: Cross‑Platform Intelligent Automated Testing System for Android and iOS

This article details ByteDance’s Fastbot system, an AI‑driven cross‑platform automated testing framework for Android and iOS that leverages model‑based testing, reinforcement learning, and image‑based UI analysis to improve test coverage, fault injection, and scalability across mobile applications and games.

AIcross-platformmobile testing
0 likes · 36 min read
Fastbot: Cross‑Platform Intelligent Automated Testing System for Android and iOS
Alimama Tech
Alimama Tech
Sep 29, 2021 · Artificial Intelligence

Unified Solution to Constrained Bidding in Online Display Advertising (USCB)

The paper proposes a unified solution for real‑time bidding in online display ads that formulates advertiser budget and KPI limits as a constrained linear program, derives a closed‑form optimal bidding function with m+1 parameters, and uses model‑free reinforcement learning to dynamically adjust those parameters, achieving superior traffic‑value capture in large‑scale deployment on Alibaba’s Taobao platform.

Parameter Tuningconstrained optimizationreal-time bidding
0 likes · 11 min read
Unified Solution to Constrained Bidding in Online Display Advertising (USCB)
Python Programming Learning Circle
Python Programming Learning Circle
Sep 27, 2021 · Artificial Intelligence

Training Reinforcement Learning Agents on Street Fighter III Using a MAME Wrapper Python Library

This tutorial explains how to install and use a Python library that wraps the MAME emulator to train reinforcement‑learning agents on arcade games such as Street Fighter III, covering system requirements, installation, environment configuration, debugging, step‑wise simulation, and a simple ConvNet agent example.

AIMAMEPython
0 likes · 4 min read
Training Reinforcement Learning Agents on Street Fighter III Using a MAME Wrapper Python Library
ByteFE
ByteFE
Aug 2, 2021 · Artificial Intelligence

An Overview of Artificial Intelligence, Machine Learning, and Neural Networks

This article provides a beginner‑friendly overview of artificial intelligence, its relationship with machine learning, the four major learning paradigms—supervised, unsupervised, semi‑supervised and reinforcement learning—along with a historical sketch of neural networks, their training workflow, loss functions, back‑propagation, and parameter‑update mechanisms, while also containing a brief recruitment notice.

Deep LearningNeural NetworksUnsupervised Learning
0 likes · 18 min read
An Overview of Artificial Intelligence, Machine Learning, and Neural Networks
DataFunSummit
DataFunSummit
Aug 1, 2021 · Artificial Intelligence

A Comprehensive Overview of Sequence Recommendation Models and Techniques

This article provides an in‑depth review of user behavior sequence recommendation, covering problem definition, data preparation, and a range of neural models—including MLP, CNN, RNN, Temporal CNN, self‑attention, and reinforcement learning—along with practical implementation tips and references.

MLNeural Networksreinforcement learning
0 likes · 35 min read
A Comprehensive Overview of Sequence Recommendation Models and Techniques
DataFunSummit
DataFunSummit
Jul 25, 2021 · Artificial Intelligence

Advances in Query Understanding and Semantic Retrieval at Zhihu Search

This article details Zhihu Search's engineering solutions for long‑tail query challenges, covering historical development, term weighting, synonym expansion, query rewriting with reinforcement learning, and semantic recall using BERT‑based models, while also outlining future research directions such as GAN‑based rewriting and lightweight pre‑training.

BERTEmbedding RetrievalQuery Rewriting
0 likes · 14 min read
Advances in Query Understanding and Semantic Retrieval at Zhihu Search
DataFunTalk
DataFunTalk
Jun 15, 2021 · Artificial Intelligence

Personalized Approximate Pareto-Efficient Recommendation (PAPERec): A Multi‑Objective Reinforcement Learning Framework for User‑Level Objective Personalization

The paper introduces PAPERec, a personalized multi‑objective recommendation framework that leverages Pareto‑oriented reinforcement learning to generate user‑specific objective weights, enabling the model to approximate Pareto‑optimal solutions and achieve superior click‑through rate and dwell‑time performance in both offline and online experiments.

CTRPareto efficiencyRecommendation Systems
0 likes · 12 min read
Personalized Approximate Pareto-Efficient Recommendation (PAPERec): A Multi‑Objective Reinforcement Learning Framework for User‑Level Objective Personalization
Alimama Tech
Alimama Tech
Jun 10, 2021 · Artificial Intelligence

Overview of Recent Alibaba Mama Research Papers Presented at KDD 2021 on Advertising and AI

At KDD 2021, Alibaba Mama presented six papers that introduced a unified constrained‑bidding solution, a deep‑learnable auction mechanism, real‑negative training for delayed‑feedback CVR, a contextual‑bandit advertising strategy recommender, a multi‑agent cooperative bidding game, and an uncertainty‑aware exploration model, all of which have been deployed to boost platform revenue and advertiser performance.

AlibabaAuction MechanismsKDD
0 likes · 16 min read
Overview of Recent Alibaba Mama Research Papers Presented at KDD 2021 on Advertising and AI
Laiye Technology Team
Laiye Technology Team
Jun 8, 2021 · Artificial Intelligence

Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue Systems

This paper presents a hierarchical reinforcement learning approach that jointly trains dialogue policy and natural language generation modules for task-oriented dialogue systems, achieving state‑of‑the‑art performance on MultiWOZ 2.0 and 2.1 while preserving response fluency.

MultiWOZdialogue policyhierarchical RL
0 likes · 10 min read
Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue Systems
DataFunTalk
DataFunTalk
Apr 24, 2021 · Artificial Intelligence

Intelligent Advertising Delivery System and Techniques: From Budget‑Constrained Bidding to Multi‑Channel Optimization

This article systematically introduces Alibaba's advertising intelligence platform, covering the evolution from basic CPM/CPC models to advanced OCPC/OCPM, budget‑constrained bidding, multi‑constraint bidding, sequence‑based long‑term value bidding, multi‑channel allocation, and the AI‑driven Smart Bidding product, highlighting algorithmic foundations, practical implementations, and performance gains.

AdvertisingMulti‑Channelbidding
0 likes · 32 min read
Intelligent Advertising Delivery System and Techniques: From Budget‑Constrained Bidding to Multi‑Channel Optimization
DataFunSummit
DataFunSummit
Mar 25, 2021 · Artificial Intelligence

An Overview of Reinforcement Learning: Concepts, Applications, Challenges, and Future Prospects

Reinforcement learning, a branch of artificial intelligence, is explained through its core concepts, successful case studies such as AlphaGo and AlphaStar, practical application workflows, current challenges, resources, and future outlook, offering a comprehensive guide for researchers and practitioners.

ApplicationsPolicy Optimizationartificial intelligence
0 likes · 56 min read
An Overview of Reinforcement Learning: Concepts, Applications, Challenges, and Future Prospects
DataFunTalk
DataFunTalk
Mar 9, 2021 · Artificial Intelligence

Introduction to Common Machine Learning Algorithms with Python Implementations

This article introduces the three main categories of machine learning—supervised, unsupervised, and reinforcement learning—detailing common algorithms such as Linear Regression, Logistic Regression, Naive Bayes, K‑Nearest Neighbors, Decision Trees, Random Forests, SVM, K‑Means, and PCA, and provides concise Python code examples using scikit‑learn for each.

PythonUnsupervised Learningmachine learning
0 likes · 18 min read
Introduction to Common Machine Learning Algorithms with Python Implementations
DataFunTalk
DataFunTalk
Feb 24, 2021 · Artificial Intelligence

Multi‑Objective Ranking in Kuaishou Short‑Video Recommendation: System Design and Online Results

This article details Kuaishou's multi‑objective ranking pipeline for short‑video recommendation, covering manual score fusion, GBDT ensemble, Learn‑to‑Rank, online auto‑tuning, ensemble sorting, reinforcement‑learning rerank, and on‑device rerank, and reports their impact on DAU, watch time and user interaction.

Kuaishoumachine learningmulti-objective ranking
0 likes · 21 min read
Multi‑Objective Ranking in Kuaishou Short‑Video Recommendation: System Design and Online Results
Architects' Tech Alliance
Architects' Tech Alliance
Jan 29, 2021 · Artificial Intelligence

Comprehensive Overview of Machine Learning: Types, Industry Chain, and Key Technologies

This article provides a detailed introduction to machine learning, covering its definition, learning modes such as supervised, unsupervised and reinforcement learning, shallow versus deep learning, the full industry chain from AI chips to cloud and big‑data services, and the major open‑source frameworks and platforms driving the field.

AI chipsBig DataUnsupervised Learning
0 likes · 11 min read
Comprehensive Overview of Machine Learning: Types, Industry Chain, and Key Technologies
Programmer DD
Programmer DD
Jan 3, 2021 · Artificial Intelligence

How Self‑Play and GAIL Powered the WeKick AI to Win the First Google Football Kaggle Championship

After a nostalgic gaming session, the author recounts how Tencent’s upgraded AI, WeKick, leveraged self‑play reinforcement learning, GAIL‑based adversarial simulation, and a multi‑style League framework to dominate the inaugural Google Football Kaggle competition, illustrating the escalating complexity of multi‑agent AI in real‑time strategy games.

GAILKaggle competitionTencent
0 likes · 8 min read
How Self‑Play and GAIL Powered the WeKick AI to Win the First Google Football Kaggle Championship
DataFunTalk
DataFunTalk
Dec 23, 2020 · Artificial Intelligence

Advances in Knowledge Graph Completion: Methods, Challenges, and Future Directions

This article reviews the rapid progress of knowledge graph completion, covering its background, formal problem definition, major technical approaches—including representation learning, path‑based search, reinforcement learning, logical reasoning, and meta‑learning—while discussing their challenges, recent improvements, and promising future research directions.

CompletionKnowledge GraphLogical Reasoning
0 likes · 14 min read
Advances in Knowledge Graph Completion: Methods, Challenges, and Future Directions
JD Cloud Developers
JD Cloud Developers
Dec 21, 2020 · Artificial Intelligence

Weekly Tech Highlights: AI Chip, Cloud Forecasts, Docker M1 Preview & More

This week’s developer newsletter spotlights the Chinese Academy of Sciences’ pioneering GNN accelerator chip, IDC’s ten cloud computing predictions for China, the booming IoT market and 5G dominance, Docker’s M1‑compatible desktop preview, a carbon‑nanotube transistor breakthrough, IBM’s FHE initiative, and recent AI research on lifelong learning and reinforcement learning exploration.

DockerHardware accelerationIoT
0 likes · 7 min read
Weekly Tech Highlights: AI Chip, Cloud Forecasts, Docker M1 Preview & More
DataFunTalk
DataFunTalk
Nov 12, 2020 · Artificial Intelligence

Reinforcement Learning for Recommendation System Mixing: Concepts, Practice, and Evaluation

This article explains how reinforcement learning, with its focus on maximizing long‑term reward, can improve recommendation system mixing by covering basic RL concepts, differences from supervised learning, multi‑armed bandit approaches, practical OpenAI Gym experiments, new AUC metrics, online gains, and advanced model optimizations.

OpenAI GymQ-LearningRecommendation Systems
0 likes · 10 min read
Reinforcement Learning for Recommendation System Mixing: Concepts, Practice, and Evaluation
Didi Tech
Didi Tech
Oct 10, 2020 · Artificial Intelligence

Deep Reinforcement Learning for Route Planning in DiDi Ride‑Hailing

DiDi’s route engine, handling over 40 billion daily requests, replaces static graph algorithms with a deep‑reinforcement‑learning system that first learns intersection decisions via behavior‑cloning LSTM models and then refines them through self‑play Q‑learning, using beam‑search decoding to produce globally optimal, low‑deviation routes for ride‑hailing.

AIBeam SearchRoute Planning
0 likes · 12 min read
Deep Reinforcement Learning for Route Planning in DiDi Ride‑Hailing
DataFunTalk
DataFunTalk
Oct 4, 2020 · Artificial Intelligence

Reinforcement Learning for Product Ranking: Model Design, Experiments, and Online Deployment

This article presents a comprehensive study of using reinforcement learning to improve e‑commerce product ranking, covering the limitations of traditional scoring, the design of context‑aware models, a pointer‑network based sequence generator, various RL algorithms, extensive offline evaluations, and successful online deployment with future research directions.

Deep LearningPPOe‑commerce
0 likes · 28 min read
Reinforcement Learning for Product Ranking: Model Design, Experiments, and Online Deployment
Sohu Tech Products
Sohu Tech Products
Sep 16, 2020 · Artificial Intelligence

Open-Domain Dialogue Systems: Current State, Challenges, and Future Directions

This article reviews the latest advances in open-domain dialogue systems, covering classification, end‑to‑end generation challenges, knowledge‑controlled generation, automated evaluation, large‑scale latent‑space models such as PLATO, and outlines future research directions for building more coherent and controllable conversational AI.

Dialogue Systemsevaluationknowledge grounding
0 likes · 14 min read
Open-Domain Dialogue Systems: Current State, Challenges, and Future Directions
MaGe Linux Operations
MaGe Linux Operations
Sep 9, 2020 · Artificial Intelligence

Master Machine Learning Basics: Concepts, Types, Algorithms & K‑NN Walkthrough

This comprehensive tutorial introduces machine learning fundamentals, its history, differences from traditional programming, key characteristics, and why Python is the preferred language, then explores supervised, unsupervised, and reinforcement learning, popular algorithms, detailed K‑Nearest Neighbors examples for classification and regression, and the essential steps to build and evaluate models.

PythonUnsupervised LearningkNN
0 likes · 21 min read
Master Machine Learning Basics: Concepts, Types, Algorithms & K‑NN Walkthrough
DataFunTalk
DataFunTalk
Aug 15, 2020 · Artificial Intelligence

Dynamic Knapsack Optimization for Multi‑Channel Sequential Advertising Using Long‑Term Value

The article presents a novel multi‑channel sequential advertising framework that models budget‑constrained GMV optimization as a dynamic knapsack problem, introduces a long‑term value‑based RL solution (MSBCB), and validates its superiority through extensive offline and online experiments showing up to 10% ROI improvement.

Advertisingbudget optimizationdynamic knapsack
0 likes · 16 min read
Dynamic Knapsack Optimization for Multi‑Channel Sequential Advertising Using Long‑Term Value
Aotu Lab
Aotu Lab
Jul 22, 2020 · Frontend Development

How Q‑Learning Can Power Smart UI Testing and Scalable Pop‑ups with Puppeteer

This article explains how reinforcement‑learning (Q‑learning) can generate mock interface data for regression testing, how Puppeteer automates UI interactions, and how a DSL‑plus‑runtime approach enables scalable pop‑up components, reducing testing costs in complex e‑commerce interactions.

AutomationPuppeteerQ-Learning
0 likes · 8 min read
How Q‑Learning Can Power Smart UI Testing and Scalable Pop‑ups with Puppeteer
DataFunTalk
DataFunTalk
Jul 21, 2020 · Artificial Intelligence

WeChat "Look" Recommendation System: Architecture, Modeling, and Engineering Challenges

This article details the end‑to‑end technical architecture of WeChat's "Look" personalized recommendation service, covering data collection, recall, multi‑stage ranking, various CTR and multi‑objective models, reinforcement‑learning based mixing, diversity optimization, and the engineering hurdles overcome to deploy these solutions at massive scale.

CTR predictionDeep LearningWeChat AI
0 likes · 17 min read
WeChat "Look" Recommendation System: Architecture, Modeling, and Engineering Challenges
58 Tech
58 Tech
Jul 8, 2020 · Artificial Intelligence

Budget Pacing Techniques and Their Application in 58.com Advertising Platform

This article introduces mainstream budget‑pacing methods for cost‑per‑click online ads, describes the 58.com business scenarios, details the pacing algorithm—including bid modification, probabilistic throttling, and reinforcement‑learning approaches—explains system design with PID control, and presents online experimental results and future directions.

Ad TechPID controlbudget allocation
0 likes · 14 min read
Budget Pacing Techniques and Their Application in 58.com Advertising Platform
Taobao Frontend Technology
Taobao Frontend Technology
Jun 30, 2020 · Frontend Development

How Reinforcement Learning Powers Front‑End Testing for Alibaba’s 618 Interactive Game

This article explains how the Taobao front‑end team tackled the complexity of the 618 interactive game by using reinforcement‑learning‑driven intelligent testing, Puppeteer‑based automated regression, and a decoupled UI‑logic architecture for scalable popup production, dramatically improving development efficiency and stability.

Automated TestingPuppeteerUI logic decoupling
0 likes · 10 min read
How Reinforcement Learning Powers Front‑End Testing for Alibaba’s 618 Interactive Game
HomeTech
HomeTech
Jun 10, 2020 · Artificial Intelligence

Exploitation & Exploration Algorithms in Recommender Systems: ε‑Greedy, UCB, and Thompson Sampling Applications

This article introduces recommender systems and the exploitation‑exploration dilemma, explains common E&E algorithms such as ε‑greedy, Upper‑Confidence‑Bound, and Thompson Sampling, and details their practical deployment for interest‑point eviction, selection, and adaptive recall count optimization in an automotive recommendation platform.

Bandit AlgorithmsEpsilon-GreedyExploitation
0 likes · 10 min read
Exploitation & Exploration Algorithms in Recommender Systems: ε‑Greedy, UCB, and Thompson Sampling Applications
DataFunTalk
DataFunTalk
May 15, 2020 · Artificial Intelligence

Optimizing Sparse Feature Embedding for Large‑Scale Recommendation and CTR Prediction

The article reviews recent research on representing massive sparse features in click‑through‑rate (CTR) models, introducing Alibaba's Res‑embedding method and Google's Neural Input Search (NIS) approach, and discusses how these techniques improve embedding efficiency and model generalization in large‑scale recommendation systems.

CTR predictionDeep LearningRecommendation Systems
0 likes · 10 min read
Optimizing Sparse Feature Embedding for Large‑Scale Recommendation and CTR Prediction
JD Retail Technology
JD Retail Technology
May 13, 2020 · Artificial Intelligence

JD's Two Papers Accepted at IJCAI2020 and SIGIR2020: Hierarchical Reinforcement Learning for Multi‑Goal Recommendation and Attention‑Based pCVR Prediction

JD announced that two of its research papers—one on a hierarchical reinforcement‑learning framework for multi‑objective recommendation (MaHRL) and another on an attention‑based model for delayed‑feedback conversion‑rate prediction (pCVR)—were accepted as full papers at the prestigious IJCAI2020 and SIGIR2020 conferences, highlighting the company's strong AI capabilities.

Recommendation Systemsartificial intelligenceconversion rate prediction
0 likes · 6 min read
JD's Two Papers Accepted at IJCAI2020 and SIGIR2020: Hierarchical Reinforcement Learning for Multi‑Goal Recommendation and Attention‑Based pCVR Prediction
Alibaba Cloud Developer
Alibaba Cloud Developer
May 11, 2020 · Artificial Intelligence

How Reinforcement Learning Revolutionizes E‑commerce Product Ranking

This article details the evolution of AliExpress product ranking from simple DNN scoring to advanced reinforcement‑learning re‑ranking, comparing multiple models, exploring context effects, introducing pointer‑network generators, evaluating various RL algorithms, and reporting significant online gains in conversion and GMV.

e‑commerceonline experimentsproduct ranking
0 likes · 28 min read
How Reinforcement Learning Revolutionizes E‑commerce Product Ranking
Alibaba Cloud Developer
Alibaba Cloud Developer
Apr 24, 2020 · Artificial Intelligence

How Reinforcement Learning Can Supercharge New Media Marketing Strategies

This article examines the limitations of traditional new media marketing, explains reinforcement learning fundamentals, and presents a six‑step technical solution—including problem modeling, algorithm selection, action, state, reward design, and model training—that uses RL to optimize budget allocation and achieve over 35% improvement in campaign effectiveness while reducing costs.

AIbudget optimizationdigital advertising
0 likes · 20 min read
How Reinforcement Learning Can Supercharge New Media Marketing Strategies
360 Quality & Efficiency
360 Quality & Efficiency
Apr 17, 2020 · Artificial Intelligence

Extending APEX for Real Distributed Reinforcement Learning with tf2rl

The article examines the limitations of the single‑machine APEX framework in the tf2rl reinforcement‑learning library, proposes a cross‑machine distributed architecture using middleware such as Redis, compares alternative frameworks like EasyRL, and outlines expected performance gains and future development plans.

APEXDistributed TrainingTensorFlow
0 likes · 5 min read
Extending APEX for Real Distributed Reinforcement Learning with tf2rl
DataFunTalk
DataFunTalk
Apr 12, 2020 · Artificial Intelligence

Wang Zhe’s Machine Learning Notes – Answers to Frequently Asked Questions on Recommendation Systems

In this article, Wang Zhe addresses fifteen common questions about recommendation systems, covering topics such as building cross‑domain knowledge, the role of deep reinforcement learning, handling sparse or low‑sample data, offline‑online evaluation, knowledge graphs, graph neural networks, model interpretability, large‑scale ID embedding, and career advice for engineers.

Deep LearningGraph Neural NetworkKnowledge Graph
0 likes · 14 min read
Wang Zhe’s Machine Learning Notes – Answers to Frequently Asked Questions on Recommendation Systems