Tagged articles
deep reinforcement learning
22 articles · Page 1 of 1
The 9th Tsinghua Big Data Intelligent Lecture gathered leading scholars and industry experts to showcase cutting‑edge research on multimodal perception, embodied intelligence, spatial AI, large‑model multimodal systems, and industrial time‑series databases, emphasizing their technical depth and real‑world impact.
GLM5V TurboSenseNovaartificial intelligence
0 likes · 8 min read

The ICLR 2026 conference announced its award winners, highlighting two Outstanding Papers—"Transformers are Inherently Succinct" and "LLMs Get Lost In Multi‑Turn Conversation"—a Honorable Mention, and two Test‑of‑Time awards for the seminal DCGAN and DDPG papers, after receiving about 19,000 submissions with a 28% acceptance rate.
Generative Adversarial NetworksICLR 2026Test of Time
0 likes · 9 min read

The paper introduces AB‑SSM, an adaptive bidirectional state‑space model that incorporates a time‑varying linear structure and a bidirectional layer to capture market non‑stationarity and asset correlations, and demonstrates through extensive US, China, and crypto experiments that it outperforms traditional, deep‑learning, and DRL baselines in profit‑risk trade‑offs, efficiency, and scalability.
adaptive linear time-varyingbidirectional SSMdeep reinforcement learning
0 likes · 12 min read

This article summarizes recent quantitative‑finance research, presenting abstracts and key findings of three papers—BPASGM for machine‑learning‑driven portfolio construction, PIKAN‑enhanced deep reinforcement learning with physics‑informed regularization, and GAPNet’s dynamic graph‑based stock relation learning—along with links to numerous related studies.
Graph Neural Networksdeep reinforcement learningmachine learning
0 likes · 11 min read

The article presents INCS, a novel framework that combines graph neural networks and deep reinforcement learning to achieve protocol‑agnostic, millisecond‑level, globally optimized network configuration synthesis, addressing scalability, protocol dependence, and lack of optimization in traditional SMT‑based methods, and demonstrates its superior performance on large‑scale topologies.
DDPGGraph Neural NetworkNetwork Synthesis
0 likes · 8 min read

Logic-Q introduces a program‑sketch paradigm that injects lightweight, plug‑and‑play market‑trend logic into deep reinforcement learning agents, dramatically improving trend detection, reducing drawdowns, and outperforming state‑of‑the‑art DRL strategies on multiple quantitative‑trading benchmarks.
Bayesian optimizationLogic-QMarket Trend Detection
0 likes · 12 min read

This roundup presents six recent arXiv papers covering crypto portfolio optimization, Sharpe‑driven stock selection with liquidity constraints, ensemble deep reinforcement learning for stock trading, dynamic machine‑learning‑based stock recommendation, a risk‑sensitive trading framework, and a generative AI model for limit order book messages, each with reported empirical results.
Quantitative Financecryptocurrencydeep reinforcement learning
0 likes · 12 min read

This study introduces DQNMaOEA, a deep reinforcement learning‑guided multi‑population coevolutionary algorithm that adaptively selects sub‑populations and allocates computational resources, achieving significantly higher solution quality and up to 25% faster runtimes on benchmark and large‑scale logistics many‑objective problems compared with state‑of‑the‑art methods.
Evolutionary Algorithmsdeep reinforcement learninglogistics
0 likes · 3 min read

This article presents a dynamic RAN slicing model and an online PW‑DRL approach that combines deep learning, reinforcement learning, and Lyapunov optimization to allocate resources adaptively, detailing a four‑step decision process, LSTM/CNN predictions, and experimental results showing improved transmission rates and acceptance ratios across DTT, DS, and TO slices.
Lyapunov optimizationNetwork SlicingOFDMA
0 likes · 6 min read

This article explains how a deep reinforcement learning model, built on a graph‑based representation of urban elements and trained with PPO, can automate land‑use and road planning to achieve Service, Ecology, and Traffic objectives for 15‑minute city neighborhoods.
15-minute cityGraph Neural NetworkPPO
0 likes · 9 min read

The forum gathers leading industry experts and scholars to discuss intelligent decision technologies across manufacturing, retail, energy, and pharmaceutical supply chains, presenting case studies, deep reinforcement learning applications, and optimization methods that drive agile, data‑driven supply chain transformation.
artificial intelligencedeep reinforcement learningindustrial engineering
0 likes · 9 min read

The article argues that the next generation GPT is likely to employ model‑based deep reinforcement learning, turning the model into both a policy and a world model, which could enable rapid, data‑efficient self‑enhancement but also raise serious safety and societal risks.
AI safetyGPT-5World Model
0 likes · 4 min read

This article introduces deep reinforcement learning by explaining its Markov decision process foundations, then categorizes the main algorithm families—value‑based methods like DQN, policy‑based approaches such as PG/DPG/DDPG, and actor‑critic techniques including A3C, PPO, and DDPG—detailing their architectures, training procedures, and key advantages.
DQNMDPactor-critic
0 likes · 14 min read

Tencent Cloud’s native database team achieved a SIGMOD breakthrough by embedding AI into MySQL, creating an autonomous “database brain” that uses deep‑reinforcement learning, genetic pre‑heating and a closed‑loop learner/actor architecture to automatically observe, analyze, and tune diverse workloads, delivering rapid performance gains, anomaly detection, and self‑optimizing features while addressing adaptability, stability, and interpretability challenges.
CDBTuneDatabase AutonomySIGMOD
0 likes · 8 min read

Tencent AI Lab’s WeKick AI clinched the inaugural Google Football Kaggle championship with a score of 1785.8, outpacing over 1,100 research teams by leveraging a migrated full‑stack architecture, custom reinforcement‑learning frameworks, GAIL imitation learning, and a multi‑style League training pipeline that together showcase the power and generality of deep reinforcement learning for complex multi‑agent tasks.
AIGAILGoogle Football
0 likes · 8 min read

This article reviews the challenges of compressing massive time‑series data, surveys existing methods, and introduces a novel two‑stage deep reinforcement learning framework (AMMMO) that adaptively selects compression modes, demonstrating significant compression ratio improvements and high throughput on large‑scale IoT and server workloads.
Data Storageadaptive algorithmsdeep reinforcement learning
0 likes · 18 min read

The report summarizes SIGMOD/PODS 2019 in Amsterdam, covering a blockchain-focused keynote, the CDBTune paper on end‑to‑end automatic cloud database tuning using deep reinforcement learning, modern hardware research, award‑winning systems, and related industry activities, providing a comprehensive academic overview.
Cloud DatabaseResearch HighlightsSIGMOD
0 likes · 7 min read

This paper introduces a novel three‑dimensional bin‑packing problem where the objective is to minimize the surface area of a single flexible container, proves its NP‑hardness, and demonstrates that a deep reinforcement learning approach using a Pointer Network improves packing efficiency by roughly five percent over traditional heuristics on real‑world data.
3D bin packingcombinatorial optimizationdeep reinforcement learning
0 likes · 16 min read

This article introduces reinforcement learning and deep reinforcement learning, explains key algorithms such as DQN and policy gradients, discusses black‑box optimization and the cross‑entropy method, and provides resources and code examples for further study.
Black-Box OptimizationDQNartificial intelligence
0 likes · 7 min read

This article explains why Alibaba's Cognitive Computing Lab uses StarCraft as a research platform, outlines the game's unique challenges for AI, and details their deep reinforcement learning and multi‑agent approaches, including the BiCNet architecture and experimental results.
AI researchBiCNetStarCraft
0 likes · 18 min read

Alibaba’s ‘Ali Xiaomi’ chatbot leverages a layered architecture that integrates intent recognition, multi‑type matching, knowledge‑graph‑based entity management, deep reinforcement learning, and hybrid retrieval‑generation models to deliver high‑accuracy, scalable conversational services across e‑commerce, customer support, and intelligent recommendation scenarios.
Natural Language Understandingchatbotdeep reinforcement learning
0 likes · 18 min read

Alibaba’s Double 11 event shattered sales records by leveraging deep reinforcement learning and adaptive online learning in its search and recommendation systems, which increased click‑through rates by 10‑20% and dramatically improved the real‑time shopping experience for hundreds of millions of users.
AI in e-commerceAlibabaadaptive online learning
0 likes · 4 min read
