267 Commits
Author SHA1 Message Date
Shangtong Zhang 8ad31c79b8 Update DDPG 2018-04-04 21:54:26 -06:00
Shangtong Zhang 61a4bcce17 Rewrite log system 2018-04-04 20:44:08 -06:00
Shangtong Zhang 0b57fdbc70 Rewrite discrete networks 2018-04-04 16:19:40 -06:00
Shangtong Zhang 63f8027199 Use openai atari wrapper 2018-04-03 20:20:18 -06:00
Shangtong Zhang e427e8f73f Add baselines' plotter 2018-04-02 15:22:56 -06:00
Shangtong Zhang e7e94d715b Add keepdim 2018-03-31 21:46:16 -06:00
Shangtong Zhang 0eaba783e8 Minor update 2018-03-24 23:21:58 -06:00
Shangtong Zhang c4adcdb6ac Update README 2018-03-22 08:33:52 -06:00
Shangtong Zhang 14d9059b5c Optimize computation of QR DQN loss 2018-03-22 00:03:38 -06:00
Shangtong Zhang 0d6e7fa54e Fix a bug of QR DQN 2018-03-21 23:49:41 -06:00
Shangtong Zhang 6863fc9c14 QR DQN Atari 2018-03-21 10:55:59 -06:00
Shangtong Zhang 4fbf811188 Quantile Regression DQN cartpole 2018-03-21 10:39:00 -06:00
Shangtong Zhang cabc95ff5d Update README 2018-03-13 20:52:51 -06:00
Shangtong Zhang 8f75029d69 Update run_iterations 2018-03-13 09:38:48 -06:00
Shangtong Zhang 174cc50440 Merge branch 'master' of https://github.com/ShangtongZhang/DeepRL 2018-03-13 09:20:26 -06:00
Shangtong Zhang d00c3b6829 Update README 2018-03-13 09:20:08 -06:00
Shangtong Zhang aa4ec06f2e N-step DQN 2018-03-12 22:42:47 -06:00
Shangtong Zhang f61908ba2a Categorical DQN for Atari 2018-03-12 21:03:38 -06:00
Shangtong Zhang 5b4ecd882e Fix a bug of Categorical DQN 2018-03-12 20:37:12 -06:00
Shangtong Zhang 3e47451ef6 Categorical DQN cart pole 2018-03-11 23:54:35 -06:00
Shangtong Zhang 1191292c51 Merge pull request #24 from nadavbh12/master
fix dataset config, handle no log dir
2018-02-27 08:27:14 -07:00
Nadav Bhonker d32627d1b5 fix dataset config, handle no log dir 2018-02-27 11:30:54 +02:00
Shangtong Zhang a907dac0bb Ram Atari 2018-02-19 13:55:57 -07:00
Shangtong Zhang 6de8062702 Code cleanup 2018-02-12 14:27:40 -07:00
Shangtong Zhang 790c8f5cb9 Orthogonal init 2018-02-12 11:58:30 -07:00
Shangtong Zhang d4aa8d4a22 Update for latest gym 2018-02-09 22:02:58 -07:00
Shangtong Zhang e7f036bc6b Update README 2018-02-09 20:45:31 -07:00
Shangtong Zhang b24593352d Remove PIL 2018-02-09 16:34:30 -07:00
Shangtong Zhang d120cf44d9 Use skimage 2018-02-09 09:55:22 -07:00
Shangtong Zhang b6436186ea Training without GAE 2018-02-03 16:46:53 -07:00
Shangtong Zhang e91ec3be45 Specify a gpu for a network 2018-02-03 10:53:14 -07:00
Shangtong Zhang fef04b6bf6 Deepmind actor-critic net 2018-02-03 09:51:52 -07:00
Shangtong Zhang e7a568598d Stack frame wrapper 2018-02-02 23:55:14 -07:00
Shangtong Zhang 8bf3a81f63 Minor update 2018-02-02 15:26:21 -07:00
Shangtong Zhang bf4ac20847 Merge pull request #22 from wassname/patch-5
load and save for SharedReplay
2018-02-02 15:23:00 -07:00
Shangtong Zhang 9896736809 Merge pull request #23 from wassname/patch-6
load_state_dict for Normalizer, StaticNormalizer
2018-02-02 15:21:35 -07:00
Shangtong Zhang 049e56e976 Minor update 2018-02-02 15:19:55 -07:00
Mike Clark db94825b19 load_state_dict for Normalizer, StaticNormalizer 2018-02-02 15:14:49 +08:00
Mike Clark 9b7d21a0f2 load and save for SharedReplay
Not sure if your interested in adding this, it just supports saving and loading SharedReplay. For example if you want to load previous DDPG experience.
2018-02-02 15:11:44 +08:00
Shangtong Zhang ad9189e25a Code cleanup 2018-01-31 21:00:19 -07:00
Shangtong Zhang 3dcda7b5d5 Update README 2018-01-31 20:21:38 -07:00
Shangtong Zhang 797f80d5ff Code cleanup 2018-01-31 20:14:33 -07:00
Shangtong Zhang ceaf83bca3 Support A2C 2018-01-31 16:19:33 -07:00
Shangtong Zhang 63c5d5ea54 Network cleanup 2018-01-19 11:29:05 -07:00
Shangtong Zhang eb16eeb2a1 Update DDPG 2018-01-19 11:24:32 -07:00
Shangtong Zhang db49a76c53 Fix a minor issue in the async demon 2018-01-17 10:43:16 -07:00
Shangtong Zhang 8224a41ba9 Update README 2018-01-01 22:49:19 -07:00
Shangtong Zhang b85ec446aa Introduce tensorboardX 2018-01-01 21:52:24 -07:00
Shangtong Zhang 71fa1aaf48 Minor fix 2018-01-01 20:45:56 -07:00
Shangtong Zhang 71002e4109 A single thread DDPG 2018-01-01 20:45:15 -07:00