191 commits

Author	SHA1	Message	Date
Antonin RAFFIN	6e470d0f72	Fix: don't change the device when saving	2020-03-31 18:38:37 +02:00
Antonin RAFFIN	2c5e41ec47	Renaming (everything plural) for consistency	2020-03-31 18:13:03 +02:00
Antonin RAFFIN	5a731d04ee	Fix docstring	2020-03-31 18:00:29 +02:00
Antonin RAFFIN	c264403816	Rename for consistency ... + add _predict to actors + improve sac actor code	2020-03-31 17:48:23 +02:00
Antonin RAFFIN	fdecd512db	Add save/load weights for policies and refactor action distributions	2020-03-31 16:29:13 +02:00
Antonin RAFFIN	fa599c65a6	Add support for Discrete observation spaces	2020-03-25 16:42:05 +01:00
Antonin RAFFIN	52d2cd6a1b	Remove gym warnings	2020-03-25 15:54:58 +01:00
Antonin RAFFIN	72a88a8d92	Fix type hint for activation fn	2020-03-24 10:10:37 +01:00
Antonin RAFFIN	ba18258af6	Add proper preprocessing	2020-03-23 17:15:30 +01:00
Antonin RAFFIN	4b2092f55a	Remove base network	2020-03-23 15:31:14 +01:00
Antonin RAFFIN	b96a081e5f	Add check for image space	2020-03-20 11:20:57 +01:00
Antonin RAFFIN	57b37513b6	Refactor handling of obs and action space ... + remove duplicated code	2020-03-20 10:09:09 +01:00
Antonin RAFFIN	fd9e73cfb8	Fix entropy computation	2020-03-19 10:19:48 +01:00
Antonin RAFFIN	9485b90a41	Sync predict with SB and add version file	2020-03-18 15:11:19 +01:00
Antonin RAFFIN	b37c23c149	Bump version and fix	2020-03-16 14:05:21 +01:00
Antonin RAFFIN	c3187604bc	Code cleanup: rename lr to lr_schedule + typing	2020-03-16 14:01:32 +01:00
Antonin RAFFIN	d4ddb3d021	Update plotter	2020-03-16 12:04:57 +01:00
Antonin Raffin	29d7018265	Add better logging for SAC and PPO	2020-03-13 11:43:12 +01:00
Antonin Raffin	c39421fa64	Fix colors in results plotter	2020-03-13 10:59:16 +01:00
Antonin Raffin	765d8fc5b2	Fix event callback	2020-03-12 13:24:11 +01:00
Antonin Raffin	b64873ffff	Sync callbacks	2020-03-12 12:34:25 +01:00
Antonin Raffin	18f38f8cf5	Reformat	2020-03-12 11:12:10 +01:00
Antonin Raffin	90d1558534	Type and reorder arguments	2020-03-11 12:45:21 +01:00
Antonin Raffin	35d0d2b320	More typing	2020-03-10 18:09:45 +01:00
Antonin Raffin	20ee8cb68d	Update changelog and add more namedtuples	2020-03-10 16:55:13 +01:00
Antonin Raffin	fb4e66213d	Use NamedTuple for buffers	2020-03-10 16:43:10 +01:00
Antonin Raffin	4392759057	Comment unused code	2020-02-14 14:15:55 +01:00
Antonin Raffin	e31b139c47	Add test for predict method	2020-02-14 14:03:41 +01:00
Antonin Raffin	8b559d71ab	Remove deprecated monitor format and improve tests	2020-02-14 13:42:16 +01:00
Antonin Raffin	a2b1bf06d3	Add squash_output attribute to policy	2020-02-14 11:12:07 +01:00
Antonin Raffin	aa8b4eb22a	Reformat and type the distributions	2020-02-13 13:46:22 +01:00
Antonin Raffin	f1a4fa2d3f	Improve predict method	2020-02-12 15:25:05 +01:00
Antonin Raffin	9caea35a11	Add results plotter	2020-02-12 14:31:15 +01:00
Antonin Raffin	7bafdb3a67	Add get_vec_normalize_env()	2020-02-12 11:34:29 +01:00
Antonin Raffin	240833ffef	Add type aliases for buffer samples	2020-02-11 17:33:22 +01:00
Antonin Raffin	2ce31c1e21	Fix entropy loss for squashed Gaussian and VecEnv seeding	2020-02-11 17:22:03 +01:00
Antonin Raffin	b7dcc8d58e	Add extend method	2020-02-11 16:40:44 +01:00
Antonin Raffin	8eb82c86e3	Save last mean reward	2020-02-11 13:22:44 +01:00
Antonin Raffin	75a86881b3	Add save/load for replay buffer	2020-02-05 13:10:02 +01:00
Antonin Raffin	31a862c3a9	Log success rate	2020-02-04 13:24:09 +01:00
Antonin Raffin	8acac6b0f4	Update docstring	2020-02-03 18:31:13 +01:00
Antonin Raffin	16121cf2b8	Create OffPolicyRLModel	2020-02-03 18:18:41 +01:00
Antonin Raffin	546fbca20c	Copy by default	2020-02-03 15:42:14 +01:00
Antonin Raffin	f7af08bea4	Refactor buffers to use numpy	2020-02-03 15:40:34 +01:00
Antonin Raffin	e3c5b1621e	Sync Monitor with Stable Baselines	2020-02-03 15:07:35 +01:00
Antonin Raffin	f0dba88275	Fix statement that had no effects	2020-02-03 10:51:29 +01:00
Antonin Raffin	6710f1576c	Fix eval log path	2020-01-31 13:48:25 +01:00
Antonin Raffin	ec657cc34e	Fix tests and change log_path behavior for EvalCallback	2020-01-31 13:42:04 +01:00
Antonin Raffin	5d4e73544c	Fix reset_num_timesteps	2020-01-31 13:16:28 +01:00
Antonin Raffin	6d59bfd4a0	Merge branch 'master' into feat/callbacks	2020-01-31 13:09:55 +01:00