reward-sharing-nash-q:改进的Nash Q学习，解决不公平的多主体游戏-源码

[{"title":"（ 57 个子文件 53KB ） reward-sharing-nash-q:改进的Nash Q学习，解决不公平的多主体游戏-源码","children":[{"title":"reward-sharing-nash-q-main","children":[{"title":"src","children":[{"title":"config","children":[{"title":"default.yaml <span style='color:#111;'> 2.01KB </span>","children":null,"spread":false},{"title":"algs","children":[{"title":"pq_dgn_q_learning.yaml <span style='color:#111;'> 514B </span>","children":null,"spread":false},{"title":"nash_q_learning.yaml <span style='color:#111;'> 544B </span>","children":null,"spread":false},{"title":"dgn_q_learning.yaml <span style='color:#111;'> 237B </span>","children":null,"spread":false}],"spread":true},{"title":"envs","children":[{"title":"surviving.yaml <span style='color:#111;'> 56B </span>","children":null,"spread":false},{"title":"gridmaze.yaml <span style='color:#111;'> 107B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"main.py <span style='color:#111;'> 3.06KB </span>","children":null,"spread":false},{"title":"run.py <span style='color:#111;'> 15.91KB </span>","children":null,"spread":false},{"title":"runner","children":[{"title":"episode_runner_nash_q.py <span style='color:#111;'> 5.17KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 299B </span>","children":null,"spread":false},{"title":"episode_runner.py <span style='color:#111;'> 5.21KB </span>","children":null,"spread":false},{"title":"pq_episode_runner.py <span style='color:#111;'> 5.98KB </span>","children":null,"spread":false}],"spread":true},{"title":"module","children":[{"title":"agents","children":[{"title":"rnn_agent.py <span style='color:#111;'> 887B </span>","children":null,"spread":false},{"title":"junk_agent.py <span style='color:#111;'> 894B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 335B </span>","children":null,"spread":false},{"title":"dgn_agent.py <span style='color:#111;'> 2.65KB </span>","children":null,"spread":false},{"title":"nash_q_agent.py <span style='color:#111;'> 10.10KB </span>","children":null,"spread":false}],"spread":true},{"title":"utils","children":[{"title":"__init__.py <span style='color:#111;'> 136B </span>","children":null,"spread":false},{"title":"components.py <span style='color:#111;'> 5.28KB </span>","children":null,"spread":false}],"spread":true},{"title":"critics","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"pq_critic.py <span style='color:#111;'> 1.81KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"env","children":[{"title":"__pycache__","children":[{"title":"multiagentenv.cpython-36.pyc <span style='color:#111;'> 2.57KB </span>","children":null,"spread":false}],"spread":true},{"title":"unfair_game","children":[{"title":"map","children":[{"title":"map5.txt <span style='color:#111;'> 51B </span>","children":null,"spread":false},{"title":"map15.txt <span style='color:#111;'> 452B </span>","children":null,"spread":false}],"spread":true},{"title":"memo.txt <span style='color:#111;'> 323B </span>","children":null,"spread":false},{"title":"go_to_star.py <span style='color:#111;'> 91B </span>","children":null,"spread":false},{"title":"gridmaze.py <span style='color:#111;'> 4.51KB </span>","children":null,"spread":false},{"title":"surviving.py <span style='color:#111;'> 6.49KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 175B </span>","children":null,"spread":false},{"title":"multiagentenv.py <span style='color:#111;'> 1.42KB </span>","children":null,"spread":false}],"spread":true},{"title":"components","children":[{"title":"transforms.py <span style='color:#111;'> 631B </span>","children":null,"spread":false},{"title":"epsilon_schedules.py <span style='color:#111;'> 833B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"action_selectors.py <span style='color:#111;'> 3.45KB </span>","children":null,"spread":false},{"title":"episode_buffer.py <span style='color:#111;'> 10.93KB </span>","children":null,"spread":false}],"spread":true},{"title":"learner","children":[{"title":"nash_q_learner.py <span style='color:#111;'> 5.77KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 272B </span>","children":null,"spread":false},{"title":"q_learner.py <span style='color:#111;'> 4.65KB </span>","children":null,"spread":false},{"title":"pq_q_learner.py <span style='color:#111;'> 6.67KB </span>","children":null,"spread":false}],"spread":true},{"title":"controller","children":[{"title":"shared_controller.py <span style='color:#111;'> 4.43KB </span>","children":null,"spread":false},{"title":"shared_controller_nash_q.py <span style='color:#111;'> 2.49KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 293B </span>","children":null,"spread":false},{"title":"separate_controller.py <span style='color:#111;'> 56B </span>","children":null,"spread":false},{"title":"basic_pq_shared_controller.py <span style='color:#111;'> 5.25KB </span>","children":null,"spread":false}],"spread":true},{"title":"utils","children":[{"title":"dict2namedtuple.py <span style='color:#111;'> 195B </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 1.61KB </span>","children":null,"spread":false},{"title":"rl_utils.py <span style='color:#111;'> 837B </span>","children":null,"spread":false},{"title":"logging.py <span style='color:#111;'> 2.37KB </span>","children":null,"spread":false},{"title":"timehelper.py <span style='color:#111;'> 1.67KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":".idea","children":[{"title":"misc.xml <span style='color:#111;'> 185B </span>","children":null,"spread":false},{"title":"vcs.xml <span style='color:#111;'> 180B </span>","children":null,"spread":false},{"title":"modules.xml <span style='color:#111;'> 294B </span>","children":null,"spread":false},{"title":"reward-sharing-nash-q.iml <span style='color:#111;'> 482B </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 47B </span>","children":null,"spread":false},{"title":"inspectionProfiles","children":[{"title":"Project_Default.xml <span style='color:#111;'> 1.02KB </span>","children":null,"spread":false},{"title":"profiles_settings.xml <span style='color:#111;'> 174B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"README.md <span style='color:#111;'> 188B </span>","children":null,"spread":false}],"spread":true}],"spread":true}]