hongshaorou/Tianshou
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Commit Graph

  • 1a164d4d7d rewrite _is_qi in a more understandable way Dong Yan 2017-12-19 00:47:21 +08:00
  • 6a410384bb rewrite _is_qi in a more understandable way Dong Yan 2017-12-19 00:47:21 +08:00
  • 243bbaff64 Merge branch 'master' of github.com:sproblvem/tianshou Dong Yan 2017-12-19 00:16:33 +08:00
  • 14da3200ff Merge branch 'master' of github.com:sproblvem/tianshou Dong Yan 2017-12-19 00:16:33 +08:00
  • fb511aa76d delete unused parameter of _find_block, and using _find_group to replace _find_block Dong Yan 2017-12-19 00:16:21 +08:00
  • ea52096713 delete unused parameter of _find_block, and using _find_group to replace _find_block Dong Yan 2017-12-19 00:16:21 +08:00
  • 0e1287b5cb update gitignore Tongzheng Ren 2017-12-18 23:34:32 +08:00
  • 6b6c48f122 update gitignore Tongzheng Ren 2017-12-18 23:34:32 +08:00
  • 27c1017259 add a detailed Chinese google coding style for convenience Tongzheng Ren 2017-12-18 23:32:41 +08:00
  • 75bc2968d2 add a detailed Chinese google coding style for convenience Tongzheng Ren 2017-12-18 23:32:41 +08:00
  • d220f7f2a8 add comments and todos 宋世虹 2017-12-17 13:28:21 +08:00
  • 7693c38f44 add comments and todos 宋世虹 2017-12-17 13:28:21 +08:00
  • 3624cc9036 finished very naive dqn: changed the interface of replay buffer by adding collect and next_batch, but still need refactoring; added implementation of dqn.py, but still need to consider the interface to make it more extensive; slightly refactored the code style of the codebase; more comments and todos will be in the next commit 宋世虹 2017-12-17 12:52:00 +08:00
  • 62e2c6582d finished very naive dqn: changed the interface of replay buffer by adding collect and next_batch, but still need refactoring; added implementation of dqn.py, but still need to consider the interface to make it more extensive; slightly refactored the code style of the codebase; more comments and todos will be in the next commit 宋世虹 2017-12-17 12:52:00 +08:00
  • 31199c7d0d 0. code refactor, try to merge Go and GoEnv Dong Yan 2017-12-16 23:29:11 +08:00
  • e10acf5130 0. code refactor, try to merge Go and GoEnv Dong Yan 2017-12-16 23:29:11 +08:00
  • 01c0c2483a check if the network weights exists for every player Dong Yan 2017-12-16 14:55:19 +08:00
  • 431f551ce9 check if the network weights exists for every player Dong Yan 2017-12-16 14:55:19 +08:00
  • d115c586d4 start the player server in a more robost way. Dong Yan 2017-12-16 14:33:31 +08:00
  • b8bdfea8bd start the player server in a more robost way. Dong Yan 2017-12-16 14:33:31 +08:00
  • 4fc50c5f1b merge class strategy with class game. Next, merge Go with GoEnv Dong Yan 2017-12-15 22:19:44 +08:00
  • 6cb4b02fca merge class strategy with class game. Next, merge Go with GoEnv Dong Yan 2017-12-15 22:19:44 +08:00
  • d0bdccc25a assign TODO to Haosheng and Tongzheng rtz19970824 2017-12-15 14:27:04 +08:00
  • 00f599bba3 assign TODO to Haosheng and Tongzheng rtz19970824 2017-12-15 14:27:04 +08:00
  • cb9540b91c Merge branch 'master' of https://github.com/sproblvem/tianshou rtz19970824 2017-12-15 14:24:15 +08:00
  • ea541ed559 Merge branch 'master' of https://github.com/sproblvem/tianshou rtz19970824 2017-12-15 14:24:15 +08:00
  • e5bf7a9270 implement dqn loss and dpg loss, add TODO for separate actor and critic rtz19970824 2017-12-15 14:24:08 +08:00
  • 0874d5342f implement dqn loss and dpg loss, add TODO for separate actor and critic rtz19970824 2017-12-15 14:24:08 +08:00
  • 92deae9f8d minor fix Haosheng Zou 2017-12-14 19:46:38 +08:00
  • 9ed3e7b092 minor fix Haosheng Zou 2017-12-14 19:46:38 +08:00
  • 039c8140e2 add dqn.py to write Haosheng Zou 2017-12-13 22:43:45 +08:00
  • f496725437 add dqn.py to write Haosheng Zou 2017-12-13 22:43:45 +08:00
  • 7ab211b63c preliminary design of dqn_example, dqn interface. identify the assign of networks Haosheng Zou 2017-12-13 20:47:45 +08:00
  • 72ae304ab3 preliminary design of dqn_example, dqn interface. identify the assign of networks Haosheng Zou 2017-12-13 20:47:45 +08:00
  • 657422a4ed
         Merge pull request #1 from sproblvem/add_rules Wenbo Hu 2017-12-13 14:35:39 +08:00
  • d280260a46 Merge pull request #1 from sproblvem/add_rules Wenbo Hu 2017-12-13 14:35:39 +08:00
  • 3f3d7b56f5 minor indent fix Wenbo Hu 2017-12-12 23:16:50 +08:00
  • d52ee30259 add nearby stones Wenbo Hu 2017-12-12 23:13:31 +08:00
  • f820aab008 change mcts steps Wenbo Hu 2017-12-12 20:37:57 +08:00
  • 848b8f0399 minor fix Wenbo Hu 2017-12-12 17:09:26 +08:00
  • 9791ad386e Merge branch 'master' of https://github.com/sproblvem/tianshou rtz19970824 2017-12-12 16:54:52 +08:00
  • 44fbccd380 add stone estimation using nearby stone for those UNKNOWs Wenbo Hu 2017-12-13 00:35:18 +08:00
  • e88d651400 minor fixed on self play rtz19970824 2017-12-11 15:56:16 +08:00
  • 715f7be6a8 update the policy rtz19970824 2017-12-11 13:38:24 +08:00
  • 0c4a83f3eb vanilla policy gradient rtz19970824 2017-12-11 13:37:27 +08:00
  • 88ecaa332d minor fix in core/policy haosheng 2017-12-11 13:25:22 +08:00
  • e3c0478fa0 Merge branch 'master' of github.com:sproblvem/tianshou Dong Yan 2017-12-10 20:23:30 +08:00
  • cacf31657b supporting self-play between different version of neural netowrks Dong Yan 2017-12-10 20:23:10 +08:00
  • 972044c39d minor fix haosheng 2017-12-10 17:33:10 +08:00
  • a00b930c2c fix naming and comments of coding style, delete .json haosheng 2017-12-10 17:23:13 +08:00
  • 0da31faa94 Merge branch 'master' of https://github.com/sproblvem/tianshou songshshshsh 2017-12-10 14:58:53 +08:00
  • f1a7fd9ee1 replay buffer initial commit songshshshsh 2017-12-10 14:53:57 +08:00
  • 9cda0bec08 coding style rtz19970824 2017-12-10 14:37:29 +08:00
  • a8a12f1083 coding style rtz19970824 2017-12-10 14:23:40 +08:00
  • d43e0fe311 minor fixed rtz19970824 2017-12-10 13:37:38 +08:00
  • cb99f6bbbb minor fixed rtz19970824 2017-12-10 13:36:43 +08:00
  • 8de92378c2 minor fixed rtz19970824 2017-12-10 13:34:07 +08:00
  • 18b3b0b850 add some TODO rtz19970824 2017-12-10 13:31:43 +08:00
  • ec6114edf1 rm ckpts rtz19970824 2017-12-09 21:53:12 +08:00
  • 0341e0d21e modify rtz19970824 2017-12-09 21:42:52 +08:00
  • 1ff8252e6d play rtz19970824 2017-12-09 21:41:11 +08:00
  • 03a6880050 Merge branch 'master' of https://github.com/sproblvem/tianshou rtz19970824 2017-12-08 23:41:51 +08:00
  • bc49d466d1 minor fixed rtz19970824 2017-12-08 23:41:31 +08:00
  • 60630c9b04 minor fixed haosheng 2017-12-08 21:18:29 +08:00
  • ff4306ddb9 model-free rl first commit, with ppo_example.py in examples/ and task delegations in ppo_example.py and READMEs haosheng 2017-12-08 21:09:23 +08:00
  • 453e457452 minor fixed rtz19970824 2017-12-08 18:59:20 +08:00
  • 8bedac5978 minor fixed rtz19970824 2017-12-08 18:08:15 +08:00
  • a381577fc7 minor fixed rtz19970824 2017-12-08 17:06:12 +08:00
  • 906ced84a3 self play rtz19970824 2017-12-08 17:05:33 +08:00
  • b687241a7d minor fix Dong Yan 2017-12-07 21:09:58 +08:00
  • 142810e95b avoid place a stone in an eye Dong Yan 2017-12-07 21:05:29 +08:00
  • 67a9a39e92 connect gtp and gui rtz19970824 2017-12-07 17:51:58 +08:00
  • 2d9d1ff945 minor fixed rtz19970824 2017-12-05 23:42:18 +08:00
  • e9beef46e4 Merge branch 'master' of https://github.com/sproblvem/tianshou rtz19970824 2017-12-05 23:20:24 +08:00
  • f9f63e6609 combine gtp and network rtz19970824 2017-12-05 23:17:20 +08:00
  • 5a88ee583b Update README.md sproblvem 2017-12-04 16:39:35 +08:00
  • e101b147b9 add example images for readme Dong Yan 2017-12-04 16:24:54 +08:00
  • 0942026e77 Update README.md sproblvem 2017-12-04 16:21:33 +08:00
  • 674ba4656b Update README.md sproblvem 2017-12-04 16:20:45 +08:00
  • 543d876f12 merge gtp rtz19970824 2017-12-04 11:01:49 +08:00
  • a60ab99e59 minor fixed rtz19970824 2017-12-03 19:18:20 +08:00
  • 7a4c5c3c88 minor fixed rtz19970824 2017-12-03 19:16:21 +08:00
  • f6d691fa90 add __init__.py mcgrady00h 2017-12-01 01:38:11 +08:00
  • 277aab59ed compute score mcgrady00h 2017-12-01 01:37:55 +08:00
  • e2ad488365 Merge branch 'master' into GTP mcgrady00h 2017-11-30 19:02:32 +08:00
  • a2040eb184 local change mcgrady00h 2017-11-30 19:01:38 +08:00
  • d24db999b9 merge gtp rtz19970824 2017-11-28 17:00:42 +08:00
  • 13738f13c4 merge gtp rtz19970824 2017-11-28 17:00:10 +08:00
  • e8c05c21cc minor fixed rtz19970824 2017-11-28 15:12:01 +08:00
  • 56012c8de9 minor fixed rtz19970824 2017-11-28 15:10:41 +08:00
  • 336a3d0020 merge rtz19970824 2017-11-28 15:05:31 +08:00
  • 2f95a1d854 remove .swp rtz19970824 2017-11-28 15:04:00 +08:00
  • f59dfda046 minor fixed rtz19970824 2017-11-28 14:53:20 +08:00
  • ead5aa83cd check valid position mcgrady00h 2017-11-28 14:47:30 +08:00
  • d508e41075 add put stone rule mcgrady00h 2017-11-28 01:15:46 +08:00
  • ca0021083f AlphaGo update rtz19970824 2017-11-26 13:36:52 +08:00
  • e727ce4d9b Merge remote-tracking branch 'origin/gtp' into HEAD rtz19970824 2017-11-25 11:26:37 +08:00
  • e4e56d17d1 minor fixed rtz19970824 2017-11-21 22:52:17 +08:00
  • 31beb46563 mcts update rtz19970824 2017-11-21 22:19:52 +08:00
  • 17a22138f7 add GTP support RenYong 2017-11-20 12:44:29 +08:00