Papers with Code 아카이브
Starcraft II
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 3
- 보존된 평가 기록
- 3
Starcraft II is a RTS game; the task is to train an agent to play the game.
<span style="color:grey; opacity: 0.6">( Image credit: The StarCraft Multi-Agent Challenge )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/oxwhirl/facmac
https://github.com/oxwhirl/smacv2
https://github.com/oxwhirl/wqmix
https://github.com/raccoon831012/StartCraft2-RL
https://github.com/ray-project/ray/tree/master/rllib
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
https://github.com/simsimiSION/pymarl-algorithm-extension-via-starcraft
https://github.com/sjtu-marl/bd_rd_psro
https://github.com/starry-sky6688/marl-algorithms
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
https://github.com/tencent-ailab/Arena
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
https://github.com/ucl-dark/pax
https://github.com/umersheikh846/WQMIX
https://github.com/uoe-agents/epymarl
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.