Commit graph

70 commits

Author SHA1 Message Date
Antonin Raffin
69a348276e Add classic advantage computation 2019-10-29 12:36:40 +01:00
Antonin Raffin
c15b4bda1e Add first draft of SDE 2019-10-28 18:24:13 +01:00
Antonin Raffin
df1e7aa000 Add docstring 2019-10-28 17:42:39 +01:00
Antonin Raffin
d67822718c Add learning rate schedule 2019-10-28 16:47:13 +01:00
Antonin Raffin
799e30ff3d Bug fixes for A2C and PPO 2019-10-28 14:27:32 +01:00
Antonin Raffin
b150167bdd Update default hyperparams 2019-10-25 13:01:00 +02:00
Antonin Raffin
584f549fa1 Bug fix for discrete actions 2019-10-25 12:00:37 +02:00
Antonin Raffin
f8bcb8ee16 Update A2C params 2019-10-25 11:31:20 +02:00
Antonin Raffin
0ad743c85d Add A2C 2019-10-25 10:59:15 +02:00
Antonin RAFFIN
3bc746c6ee Add logger for PPO 2019-10-17 13:44:48 +02:00
Antonin RAFFIN
53898f3d1a Add flexible mlp 2019-10-17 13:32:25 +02:00
Antonin Raffin
64de9923d6 Buf fixes for python 2 2019-10-15 13:24:53 +02:00
Antonin Raffin
ab64ff464e Add tensorboard_log dummy arg 2019-10-14 11:09:22 +02:00
Antonin Raffin
b5656531d1 Enable logger for SAC/TD3 + refactor 2019-10-10 13:47:13 +02:00
Antonin Raffin
dbaa5daca6 Add logger and Monitor wrapper 2019-10-10 13:41:54 +02:00
Antonin Raffin
ef50bb81e8 Add support for categorical distribution 2019-10-08 13:06:38 +02:00
Antonin Raffin
4d0c033bf2 Bug fix when randomly sampling actions 2019-10-07 16:36:48 +02:00
Antonin Raffin
37ab9d10f1 Rescale actions and add action noise 2019-10-07 16:26:03 +02:00
Antonin RAFFIN
12f854e1aa Fix learning starts 2019-10-01 21:56:37 +02:00
Antonin Raffin
440166fe26 Add a parameter to disable ortho init 2019-09-26 16:29:47 +02:00
Antonin Raffin
b4dc9d4e4d Add doc 2019-09-26 11:46:40 +02:00
Antonin Raffin
70e5de1d1b Update SAC defaults 2019-09-25 17:07:54 +02:00
Antonin Raffin
0e4fc9c0ac Bug fix SAC 2019-09-25 13:30:08 +02:00
Antonin Raffin
322399e8fe Update collect rollout 2019-09-25 13:20:06 +02:00
Antonin Raffin
6bfbb7198a Rename seed 2019-09-24 16:59:47 +02:00
Antonin Raffin
32648d9029 Add docstrings 2019-09-24 15:30:58 +02:00
Antonin Raffin
f4fe1362f0 Renaming 2019-09-24 14:53:03 +02:00
Antonin Raffin
d22caac616 Working SAC 2019-09-24 14:15:12 +02:00
Antonin RAFFIN
98e9560913 Remove note 2019-09-22 21:33:35 +02:00
Antonin RAFFIN
1bd2e42995 Add a note for squashed gaussian 2019-09-22 14:15:22 +02:00
Antonin RAFFIN
b157b4465a Add logo 2019-09-22 13:57:18 +02:00
Antonin RAFFIN
7627a8644c Add roadmap 2019-09-22 13:43:01 +02:00
Antonin RAFFIN
8adb8f9931 Change default dist to gaussian 2019-09-22 12:56:27 +02:00
Antonin RAFFIN
ddaafcbc36 Refactor: add distributions 2019-09-22 12:52:49 +02:00
Antonin RAFFIN
70e1d673a9 Separate policy and value net 2019-09-21 18:12:06 +02:00
Antonin RAFFIN
2469ff3859 Reformat 2019-09-21 17:17:09 +02:00
Antonin RAFFIN
3ececcd3a9 Add tensorboard example 2019-09-21 17:09:26 +02:00
Antonin RAFFIN
e8ddd1f901 Improve initialization 2019-09-21 16:48:51 +02:00
Antonin RAFFIN
dfe1ab9690 Revert buffer update 2019-09-21 16:03:22 +02:00
Antonin RAFFIN
a196306d9e Update replay buffer 2019-09-21 15:54:26 +02:00
Antonin RAFFIN
bcdd99d22c Fix deterministic run 2019-09-21 15:53:28 +02:00
Antonin Raffin
a9b8276efb Attempt to fix loss of perf because of VecEnvs 2019-09-20 18:06:08 +02:00
Antonin Raffin
0e727a5f72 Full compat for VecEnv + bug fixes for cuda 2019-09-20 16:43:19 +02:00
Antonin Raffin
255ff10bff PPO VecEnv compat 2019-09-20 15:19:04 +02:00
Antonin Raffin
56053bc692 Add stable-baselines VecEnvs 2019-09-20 15:18:25 +02:00
Antonin RAFFIN
cc4380eccd Add eval env and clip vf 2019-09-19 17:18:41 +02:00
Antonin RAFFIN
fe8b415cbf First sign of life 2019-09-19 16:21:28 +02:00
Antonin RAFFIN
ad089f5b19 Add explained variance 2019-09-19 11:43:27 +02:00
Antonin RAFFIN
26f0c8d8e5 Refactor buffer 2019-09-19 11:43:15 +02:00
Antonin RAFFIN
149148d4c7 Bug fix actor forward 2019-09-18 23:55:41 +02:00