Papers with Code 아카이브

Real-Time Strategy Games

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 2
평가표: 0
보존된 평가 기록: 0

Real-Time Strategy (RTS) tasks involve training an agent to play video games with continuous gameplay and high-level macro-strategic goals such as map control, economic superiority and more.

<span style="color:grey; opacity: 0.6">( Image credit: Multi-platform Version of StarCraft: Brood War in a Docker Container )</span>

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/deepmind/diplomacy

공식 코드

Learning to Play No-Press Diplomacy with Best Response Policy Iteration

https://github.com/deepmind/pushworld

공식 코드

PushWorld: A benchmark for manipulation planning with tools and movable obstacles

https://github.com/deepmind/pysc2

공식 코드

StarCraft II: A New Challenge for Reinforcement Learning

https://github.com/devindeng94/llm-smac

공식 코드

A New Approach to Solving SMAC Task: Generating Decision Tree Code from Large Language Models

https://github.com/devindeng94/smac-hard

공식 코드

SMAC-Hard: Enabling Mixed Opponent Strategy Script and Self-play on SMAC

https://github.com/dig-beihang/ami

공식 코드

Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence

https://github.com/facebook/MazeBase

공식 코드

MazeBase: A Sandbox for Learning from Games

https://github.com/facebookresearch/CollaQ

공식 코드

Multi-Agent Collaboration via Reward Attribution Decomposition

https://github.com/facebookresearch/ELF

공식 코드

ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games

https://github.com/facebookresearch/diplomacy_searchbot

공식 코드

No-Press Diplomacy from Scratch

https://github.com/facebookresearch/nle

공식 코드

Dungeons and Data: A Large-Scale NetHack Dataset

https://github.com/facebookresearch/starcraft_defogger

공식 코드

Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger

https://github.com/flairox/jaxmarl

공식 코드

JaxMARL: Multi-Agent RL Environments and Algorithms in JAX

https://github.com/hahayonghuming/VDACs

공식 코드

Value-Decomposition Multi-Agent Actor-Critics

https://github.com/hanhanAnderson/LSF-SAC

공식 코드

Value Functions Factorization with Latent State Information Sharing in Decentralized Multi-Agent Policy Gradients

https://github.com/hanhananderson/pac-marl

공식 코드

PAC: Assisted Value Factorisation with Counterfactual Predictions in Multi-Agent Reinforcement Learning

https://github.com/hijkzzz/pymarl2

공식 코드

Rethinking the Implementation Matters in Cooperative Multi-Agent Reinforcement Learning

https://github.com/histmeisah/large-language-models-play-starcraftii

공식 코드

Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach

https://github.com/hsvgbkhgbv/shapley-q-learning

공식 코드

SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning

https://github.com/hyeon1996/fox

공식 코드

FoX: Formation-aware exploration in multi-agent reinforcement learning

https://github.com/hyunghona/emu

공식 코드

Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning

https://github.com/j3soon/dfac

공식 코드

DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning

https://github.com/j3soon/dfac-extended

공식 코드

A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning

https://github.com/jiwonjeon9603/maser

공식 코드

MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer

https://github.com/jjbong/strangeness_exploration

공식 코드

Strangeness-driven Exploration in Multi-Agent Reinforcement Learning

https://github.com/jramapuram/variational_saccading

공식 코드

Variational Saccading: Efficient Inference for Large Resolution Images

https://github.com/junaiddk/transmix

공식 코드

Transformer-based Value Function Decomposition for Cooperative Multi-agent Reinforcement Learning in StarCraft

https://github.com/kaszanas/sc2_datasets

공식 코드

SC2EGSet: StarCraft II Esport Replay and Game-state Dataset

https://github.com/kkane99/MANGER_code

공식 코드

Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning

https://github.com/kkane99/manger

공식 코드

Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning

https://github.com/liuruoze/Raw-vs-Human-in-AlphaStar

공식 코드

Rethinking of AlphaStar

https://github.com/liuruoze/hiernet-sc2

공식 코드

On Efficient Reinforcement Learning for Full-length Game of StarCraft II

https://github.com/liuruoze/mini-AlphaStar

공식 코드

An Introduction of mini-AlphaStar

https://github.com/liuruoze/thought-sc2-model-experiment

공식 코드

Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning

https://github.com/luchang1113/hep-llm-play-starcraftii

공식 코드

Hierarchical Expert Prompt for Large-Language-Model: An Approach Defeat Elite AI in TextStarCraft II for the First Time

https://github.com/lucidrains/perceiver-pytorch

공식 코드

Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.