Commit graph

26 commits

Author SHA1 Message Date
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
Antonin RAFFIN
525fe43552 Bug fix rollout buffer 2019-09-18 23:48:47 +02:00
Antonin RAFFIN
e1c1d5c4ab Bug fixes (not working yet) 2019-09-18 22:12:32 +02:00
Antonin RAFFIN
6bb7e183d2 Running PPO (not working yet) 2019-09-18 15:35:17 +02:00
Antonin Raffin
54dd7ea60d Start PPO 2019-09-18 13:10:27 +02:00
Antonin Raffin
2a660e9a41 Update closer to original implementation for CEMRL 2019-09-12 15:38:15 +02:00
Antonin Raffin
f04754afec Refactor for collecting rollout 2019-09-12 14:00:55 +02:00
Antonin Raffin
5e3a84d551 Refactor policies 2019-09-12 11:19:06 +02:00
Antonin Raffin
c3c87f8311 Add update styles for CEM-RL 2019-09-10 13:07:15 +02:00
Antonin Raffin
d22b66fc10 Fixes for CUDA support 2019-09-09 16:45:55 +02:00
Antonin Raffin
d333abe963 Remove stdout flush 2019-09-09 13:51:18 +02:00
Antonin Raffin
12431b0e92 Refactor: CEM-RL closer to TD3 implementation 2019-09-09 13:43:46 +02:00
Antonin Raffin
6cce61d183 Fix random exploration 2019-09-06 14:11:27 +02:00
Antonin Raffin
5e38080937 Code cleanup 2019-09-06 14:04:40 +02:00
Antonin Raffin
d4e2dc8a9c Add CEM-RL 2019-09-06 14:01:10 +02:00
Antonin Raffin
90882ee846 Fixes for python 2 + env from string 2019-09-06 11:46:25 +02:00
Antonin Raffin
904742714d Fixes for python 2 2019-09-06 11:43:02 +02:00
Antonin Raffin
68028c71a1 Seed env + fix max action 2019-09-06 11:09:56 +02:00
Antonin Raffin
9cf289b997 Bug fixes + add evaluate script 2019-09-06 10:44:55 +02:00
Antonin Raffin
46d8d9725b Init: TD3 2019-09-05 17:29:41 +02:00
Raffin, Antonin
ad6076bb7a Initial commit 2019-09-05 13:26:14 +02:00