Papers with Code 아카이브
Dota 2
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Dota 2 is a multiplayer online battle arena (MOBA). The task is to train one-or-more agents to play and win the game.
<span style="color:grey; opacity: 0.6">( Image credit: OpenAI Five )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/liyiyuian/Deep-Learning
https://github.com/llSourcell/OpenAI_Five_vs_Dota2_Explained
https://github.com/mark-gluzman/NmodelPPO
https://github.com/marload/DeepRL-TensorFlow2
https://github.com/michael-snower/ppo
https://github.com/microsoft/strategically_efficient_rl
https://github.com/mightypirate1/PPO_homebrew
https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore
https://github.com/miroblog/tf_deep_rl_trader
https://github.com/mit-realm/neuriss
https://github.com/montaserFath/Reinforcement-Learning-for-Prosthetics
https://github.com/morikatron/GAIL_PPO
https://github.com/morikatron/PPO
https://github.com/near32/regym
https://github.com/nikhilbarhate99/PPO
https://github.com/nikhilbarhate99/PPO-PyTorch
https://github.com/nitthilan/pommerman
https://github.com/nric/ProximalPolicyOptimizationContinuousKeras
https://github.com/nvlabs/gbrl_sb3
https://github.com/opendilab/DI-engine/blob/main/ding/policy/collaq.py
Multi-Agent Collaboration via Reward Attribution Decomposition
https://github.com/openpsi-projects/srl
https://github.com/petuum/adaptdl
https://github.com/pytorch/rl/tree/main/examples/ppo
https://github.com/ray-project/ray/tree/master/rllib
https://github.com/reinforcement-learning-kr/pg_travel
https://github.com/rshnn/battleship
https://github.com/s-sd/task-amenability
https://github.com/sandeeprockstar/Pose_Estimation
https://github.com/sarahisyoung/rlpyt
https://github.com/saschaschramm/Pong
https://github.com/sc2crazy/StarCrackRL
https://github.com/seungjaeryanlee/osim-rl-helper
https://github.com/shiningsunnyday/mcts-chess
https://github.com/shreyesss/PPO-implementation-keras-tensorflow
https://github.com/shuishida/soaprl
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.