Papers with Code 아카이브

Starcraft

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 0
보존된 평가 기록: 0

Starcraft I is a RTS game; the task is to train an agent to play the game.

<span style="color:grey; opacity: 0.6">( Image credit: Macro Action Selection with Deep Reinforcement Learning in StarCraft )</span>

코드

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

https://github.com/tencent-ailab/Arena

Arena: a toolkit for Multi-Agent Reinforcement Learning

https://github.com/tjuhaoxiaotian/pymarl3

The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games

https://github.com/tumcps/commonpower

The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games

https://github.com/tuomaso/SC2LE-implementation

StarCraft II: A New Challenge for Reinforcement Learning

https://github.com/ucl-dark/pax

JaxMARL: Multi-Agent RL Environments and Algorithms in JAX

https://github.com/umersheikh846/WQMIX

Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

https://github.com/universome/stylegan-v

Towards Accurate Generative Models of Video: A New Metric & Challenges

https://github.com/uoe-agents/epymarl

The StarCraft Multi-Agent Challenge

https://github.com/wilson1yan/VideoGPT

Towards Accurate Generative Models of Video: A New Metric & Challenges

https://github.com/xiuyu0000/new_papers_codes/tree/main/mappo

The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games

https://github.com/xiuyu0000/new_papers_codes/tree/main/qmix

QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

https://github.com/zoeyuchao/mappo

The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games

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