Tagged articles
game AI
32 articles · Page 1 of 1
The article surveys ten community-built demos of the Jev model — a specialized decision-making LLM from a former OpenAI researcher — showing it driving 50 parallel Subway Surfers games, beating Super Mario Bros, piloting a rocket in MuJoCo, analyzing 724 ads in 40 seconds, and filtering AI tool-call histories, all at sub-cent costs and ~0.7 s per decision.
Jevbrowser automationdecision-making LLM
0 likes · 13 min read

This article analyzes TypeSafe's Jev, a specialized decision model that returns structured choices, scores, or boolean judgments for high-frequency agent tasks like game AI, browser automation, and ticket triage, offering lower latency and cost than LLMs by narrowing training to calibrated classification with confidence gating.
Agent RoutingDecision ModelJev
0 likes · 17 min read

The article examines the limitations of one‑shot AI game generation—prompt randomness and inflated self‑scoring—and introduces CreativeGame, a research‑backed framework that enforces mechanic‑aware, iterative design, lineage‑aware memory, and deterministic reward signals to achieve genuine, evolvable game creativity.
AI game generationCreativeGameLLM creativity
0 likes · 14 min read

Google DeepMind has taken a stake in the developers of EVE Online, planning to run a dedicated offline version of the massive, player‑driven sandbox game to conduct controlled AI experiments that explore long‑term planning, memory, and continual learning in a richly simulated universe.
Citizen ScienceDeepMindEVE Online
0 likes · 7 min read

This article details a custom Three‑Kingdoms‑style strategy game used to benchmark nine flagship large language models, explains the game mechanics, evaluates each model's strategic decisions and diplomatic behavior, and reveals how Gemini 3.1 Pro clinched the championship with a clever "坚壁清野" tactic while also sharing the underlying engine architecture and development lessons.
LLMStrategy EvaluationThree Kingdoms
0 likes · 29 min read

Game‑TARS, a general‑purpose game AI from ByteDance's Seed team, replaces custom function calls with low‑level keyboard‑mouse actions, leverages massive multimodal data, sparse‑thinking and decaying‑loss algorithms, and achieves zero‑shot mastery across diverse games, surpassing top large models like GPT‑5 and Gemini‑2.5‑Pro.
AI TrainingMultimodal Datagame AI
0 likes · 10 min read

In a Silicon Valley tech conference, Mu Shen shared how voice agents—real‑time, task‑oriented AI—were applied to an open‑world game as an AI NPC and to a Fortune‑500 insurer as an AI tele‑salesperson, revealing technical challenges, model architectures, training strategies, evaluation methods, and key lessons for future deployments.
game AIinsurance automationlarge language models
0 likes · 19 min read

The report analyzes how AI is reshaping every stage of game creation and experience, highlighting developer adoption rates, advances in asset generation, narrative design, testing, commercialization, and the broader market transformation driven by generative AI technologies.
AIAIGCgame AI
0 likes · 7 min read

This article details the author's experience designing a top‑performing AI Werewolf agent for the Taotian Group's AI Werewolf Challenge, covering game rules, core challenges, prompt engineering, caching, concurrent requests, model selection, reinforcement‑learning‑style tuning, and tactical strategies for each role, with code examples.
AI agentLLMWerewolf
0 likes · 25 min read

This article provides a step‑by‑step guide, complete with Python code examples, for creating a Protoss AI bot using DeepMind's pysc2 library to mine resources, construct buildings, train units, implement scouting, and execute attack strategies against increasingly difficult computer opponents in StarCraft II.
AI BotDeepMindStarCraft II
0 likes · 28 min read

This article explains the design, implementation, and underlying Agent‑Oriented‑Programming framework of NetEase Fuxi’s multimodal real‑time voice AI teammate for the mobile game ‘Naraka: Bladepoint’, highlighting its capabilities such as autonomous navigation, combat assistance, natural dialogue, teaching, and broader applications of voice technology in games.
Naraka Bladepointagent-oriented programminggame AI
0 likes · 12 min read

NetEase’s AI team reveals how their self‑developed distributed reinforcement‑learning platform, Bray, enables high‑level AI agents for the MOBA game Dream of Kingdom 2, covering GameCore integration, weighted random initialization, modular APIs, difficulty scaling, and cost‑effective training for realistic player experiences.
AI frameworkMoBAdistributed training
0 likes · 9 min read

This article reviews the evolution of game AI agents, examines how large language models (LLMs) can drive new AI behaviors in games, and discusses practical case studies across genres such as Werewolf‑style, war‑SLG, and MOBA games, concluding with challenges and future research directions.
AI agentsLLMLanguage Model
0 likes · 31 min read

The article details NetEase Fuxi's research on AI‑Generated Action (AIGA) for game AI bots, covering the shift from AIGC to AIGA, advances in making bots more human‑like and stylized, and the application of RLHF fine‑tuning to bridge objective metrics with subjective player experience.
AIAIGAHuman-like Bots
0 likes · 20 min read

Tencent Robotics X unveiled how its robot dog Max combines pre‑trained AI models with reinforcement learning across three learning stages, enabling it to acquire, store, and apply skills for autonomous decision‑making in complex tasks such as the World Chase Tag competition.
AIRoboticsSimulation
0 likes · 6 min read

This article details NetEase Zhiji and Dianhun Network's use of reinforcement learning, a distributed training framework, and middleware to create, train, deploy, and iterate AI robots for the game "Barbarian Battle 2", highlighting technical challenges, solutions, and the impact on player experience.
AI botsdistributed traininggame AI
0 likes · 13 min read

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

This article explains what artificial intelligence is, distinguishes weak and strong AI, explores its applications in games, product testing, and NetEase's Fuxi platform, and introduces fundamental machine‑learning concepts such as supervised, unsupervised, and reinforcement learning, as well as neural networks and loss functions.
AIgame AImachine learning
0 likes · 10 min read

This article explains how to build a Tetris game with a basic AI using Python 3.6.4 and PyQt5, covering environment setup, the underlying algorithm that evaluates future board states, and the complete source code for the AI decision‑making and scoring functions.
PythonTetrisgame AI
0 likes · 6 min read

Zheng Lin‑kai’s record‑breaking Tetris AI for the Tencent Geek Challenge combines a two‑layer breadth‑first search—stage‑level pruning in Python and fast round‑level BFS in C++—with a heuristic that rewards high score, low occupied cells, and smooth board transitions, enabling a 1,413,876‑point performance.
C++Monte Carlo Tree SearchPython
0 likes · 10 min read

This article details a graduate student's AI‑driven solution to the Tencent Geek Competition's "E‑Tetris" challenge, describing the EI‑Tetris heuristic, feature‑based evaluation, state‑pruned dynamic programming, C++ implementation, performance results, and potential improvements.
Algorithm CompetitionC++Evaluation Function
0 likes · 12 min read

This article explains how to create an AI‑driven Dou Dizhu card‑playing assistant by integrating the open‑source DouZero model with a PyQt5 GUI, covering UI layout, hand‑card and role recognition via screen capture, AI decision making, and step‑by‑step deployment instructions.
AICard RecognitionDouZero
0 likes · 17 min read

Tencent’s open‑source Game AI SDK provides a versatile automation testing platform—supporting a wide range of game genres and mobile/PC apps—by integrating environment simulation, configurable tools, image‑recognition modules, and deep‑learning algorithms (DQN and IM) into a unified, user‑friendly workflow for training and executing AI agents.
Automation TestingSDKTensorFlow
0 likes · 17 min read

This article explains how to apply the Expectimax search algorithm to the 2048 puzzle game, detailing the game mechanics, problem formulation, scoring heuristics, pseudocode, and performance optimizations to choose the best move at each step despite the game's randomness.
2048Expectimaxgame AI
0 likes · 10 min read

From Steve Jobs’s early work at Atari to modern DeepMind breakthroughs, the article traces how video games have grown into a multibillion‑dollar industry that serves as a testbed for AI research, while highlighting current AI techniques for smarter agents, procedural content generation, and the collaborative challenges shaping the future of game development.
Monte Carlo Tree Searchartificial intelligencegame AI
0 likes · 25 min read

This tutorial explains how to capture screen images from GTA V (or similar games) using Python and OpenCV, covering screen grabbing, converting to NumPy arrays, handling performance, and setting up basic input simulation to enable AI-driven autonomous driving experiments.
Computer VisionGTA Vgame AI
0 likes · 6 min read

This article traces the history of game artificial intelligence—from early MiniMax chess programs and classic board‑game breakthroughs like Deep Blue, through AlphaGo’s triumph over human champions, to the self‑learning AlphaGo Zero—while explaining why games serve as a vital testbed for modern AI research.
AlphaGogame AImachine learning
0 likes · 13 min read

The talk surveyed game‑AI evolution—from rule‑based systems to AlphaGo‑style reinforcement learning—highlighted industry and academic methods, detailed challenges of applying deep‑learning techniques to MOBA titles like Honor Kings, and proposed a hierarchical, multimodal framework with analysis and execution modules supported by robust simulation environments.
AI in GamesAlphaGoMoBA
0 likes · 10 min read

This article explains how deep reinforcement learning, built upon traditional Q‑learning and enhanced with techniques like experience replay, enables agents to play Atari video games directly from raw pixel inputs, illustrating the key differences, processing steps, and the significance of this breakthrough in AI.
AtariQ-Learningdeep Q‑learning
0 likes · 5 min read

This tutorial walks through using Python and OpenCV to capture screen images from GTA V, covering screen grabbing, converting to NumPy arrays, improving frame rates, handling key and controller input, and setting up a basic autonomous driving test environment, all without relying on pre‑existing libraries.
Computer VisionGTA VOpenCV
0 likes · 7 min read

This article explains how to use a Python implementation of the minimax algorithm to analyze a Doudizhu end‑game scenario, detailing the core logic, recursive hand simulation, caching optimizations, and the final result that the farmer side has no guaranteed winning strategy.
AlgorithmDoudizhuMiniMax
0 likes · 6 min read


ArchitectMar 10, 2016 · Artificial Intelligence
This article explains Monte Carlo Tree Search (MCTS), covering its origin in AlphaGo, fundamental algorithm steps, node‑selection strategies such as UCB, strengths and weaknesses, enhancements, historical background, and recent research developments in artificial intelligence.
MCTSMonte Carlo Tree SearchSearch Algorithms
0 likes · 12 min read
