Commit Graph
219 Commits
Author SHA1 Message Date
Shangtong Zhang bc89bb2eed Init FCBody 2018-04-27 16:31:33 -06:00
Shangtong Zhang 6f3c26a5a8 Refactor fully-connected body 2018-04-27 16:29:22 -06:00
Shangtong Zhang cce767692e Refactor tasks 2018-04-27 16:23:30 -06:00
Shangtong Zhang d2c8a985d5 Remove OU process 2018-04-26 14:41:35 -06:00
Shangtong Zhang 3eb6682551 Update DDPG 2018-04-26 12:20:11 -06:00
Shangtong Zhang a5a5cf54b4 Update DDPG parameters 2018-04-26 11:53:07 -06:00
Shangtong Zhang 8d19314360 Update plot utility 2018-04-26 11:48:51 -06:00
Shangtong Zhang 2eefb04b9d Refactor DDPG 2018-04-25 23:38:17 -06:00
Shangtong Zhang ceea0a474b Update networks for continuous control 2018-04-25 21:26:58 -06:00
Shangtong Zhang 4f2903eb8f Fix a bug for GPU 2018-04-25 17:01:05 -06:00
Shangtong Zhang 6f517e3eef Update README 2018-04-24 23:40:07 -06:00
Shangtong Zhang 6b16b5476f Update README 2018-04-24 23:37:26 -06:00
Shangtong Zhang d0b4f496f3 Update README 2018-04-24 23:33:05 -06:00
Shangtong Zhang be4f2720fe Update README 2018-04-24 23:29:22 -06:00
Shangtong Zhang ab1f46beaf Update README 2018-04-24 23:22:20 -06:00
Shangtong Zhang c7ceb876dd Upgrade to PyTorch v0.4 2018-04-24 23:10:09 -06:00
Shangtong Zhang fc7cfdf095 Add requirements.txt 2018-04-24 22:12:08 -06:00
Shangtong Zhang f2db4e8819 Support gym robotics 2018-04-24 21:49:25 -06:00
Shangtong Zhang 92f0366175 Refactor replay 2018-04-21 11:21:48 -06:00
Shangtong Zhang e733b13a8f Update plotter and scheduler 2018-04-21 10:26:44 -06:00
Shangtong Zhang b6668fc374 Minor fix for python 2.7 2018-04-20 16:01:57 -06:00
Shangtong Zhang c7ad749058 Refactor networks 2018-04-20 15:53:43 -06:00
Shangtong Zhang 567e0876c1 Update evaluation scheme 2018-04-20 11:37:19 -06:00
Shangtong Zhang 08d45b9284 Timestep based test scheme 2018-04-12 22:23:21 -06:00
Shangtong Zhang de478faf9b Remove unused variables 2018-04-12 22:04:56 -06:00
Shangtong Zhang f255c6ed25 Update logger 2018-04-12 22:02:16 -06:00
Shangtong Zhang aef2e71ed1 Update README 2018-04-11 08:35:24 -06:00
Shangtong Zhang a27cf0aa4e Minor update 2018-04-10 23:57:53 -06:00
Shangtong Zhang ad6acdeca0 PPO Atari 2018-04-10 23:52:26 -06:00
Shangtong Zhang e1df46aeec Minor update 2018-04-10 23:40:45 -06:00
Shangtong Zhang bb5ef4fbfc Discrete PPO cartpole 2018-04-10 23:37:12 -06:00
Shangtong Zhang 015c7753ea Continuous actor critic wrapper 2018-04-10 23:15:33 -06:00
Shangtong Zhang f6854a4917 Update README 2018-04-10 11:34:15 -06:00
Shangtong Zhang 669c366bc0 Update ACVP 2018-04-10 11:32:59 -06:00
Shangtong Zhang af1cc11669 Update ACVP 2018-04-10 11:25:59 -06:00
Shangtong Zhang 3254809162 Clip gradients for DQN and NStepQ 2018-04-10 10:18:44 -06:00
Shangtong Zhang 5b77fae4cb Support deterministic test episode 2018-04-08 23:00:37 -06:00
Shangtong Zhang 8f5b7bf222 Update README 2018-04-08 10:15:32 -06:00
Shangtong Zhang 2ff8002c69 Update README 2018-04-08 09:40:04 -06:00
Shangtong Zhang 7b0c434289 Update figures 2018-04-08 09:39:20 -06:00
Shangtong Zhang e2eb09e9a6 Update reference 2018-04-08 09:37:24 -06:00
Shangtong Zhang c9164adb65 Update README 2018-04-08 09:32:40 -06:00
Shangtong Zhang 332d7ac78f Update README 2018-04-08 09:26:24 -06:00
Shangtong Zhang d9b49f9a7e Update README 2018-04-08 09:24:09 -06:00
Shangtong Zhang 45587b9cce Update PPO 2018-04-08 09:14:35 -06:00
Shangtong Zhang 0f3f49252b Support DM Control 2018-04-07 20:53:29 -06:00
Shangtong Zhang 8623fe849b Regenerate images 2018-04-07 10:11:33 -06:00
Shangtong Zhang 276d00374a Update ACVP and plotter 2018-04-06 16:40:48 -06:00
Shangtong Zhang 8dfe6ff7c8 Rewrite state/reward normalizer 2018-04-06 11:36:44 -06:00
Shangtong Zhang 4c6481d5be Tune parameters for DDPG 2018-04-06 10:34:52 -06:00