stable-baselines3/stable_baselines3/common
Antonin RAFFIN d7c6aff252
Fix discrete obs support (#296)
* Fixed discrete obs support

* Suggest new edit, fix failed test

* Revert "Suggest new edit, fix failed test"

This reverts commit 6892bf05506bb5ad0e87016d8d382705ab72e6a4.

* Fix test

* Special case for discrete obs

Co-authored-by: Anssi "Miffyli" Kanervisto <kaneran21@hotmail.com>
2021-01-21 02:42:33 +02:00
..
sb2_compat Add callable signatures to type annotations. (#215) 2020-11-15 17:50:28 +01:00
vec_env Use Monitor episode reward/length for evaluate_policy (#220) 2020-11-16 11:52:28 +01:00
__init__.py Update docs (custom policy, type hints) (#167) 2020-09-29 20:41:14 +03:00
atari_wrappers.py Add SUMO-RL as example project in the docs (#257) 2020-12-13 17:15:45 +01:00
base_class.py Add supported action spaces checks (#254) 2020-12-06 14:05:10 +02:00
bit_flipping_env.py Implement HER (#120) 2020-10-22 11:56:43 +02:00
buffers.py Fix discrete obs support (#296) 2021-01-21 02:42:33 +02:00
callbacks.py Add eval success rate logging (#255) 2020-12-08 15:49:07 +01:00
cmd_util.py Fix off policy features extractor (#198) 2020-10-27 14:24:59 +01:00
distributions.py Fix off policy features extractor (#198) 2020-10-27 14:24:59 +01:00
env_checker.py add check to ensure action space is non-dict non-tuple for env_checker nan check (#192) 2020-10-19 00:23:51 +03:00
env_util.py Doc fixes and add monitor_kwargs parameter (#230) 2020-11-20 10:28:54 +01:00
evaluation.py Use Monitor episode reward/length for evaluate_policy (#220) 2020-11-16 11:52:28 +01:00
identity_env.py Avoid transposing channel-first envs (#213) 2020-11-03 12:34:09 +01:00
logger.py Add image and figure to tensorboard logger (#277) 2021-01-08 15:47:08 +01:00
monitor.py Improve typing coverage (#175) 2020-10-07 10:51:49 +02:00
noise.py Improve typing coverage (#175) 2020-10-07 10:51:49 +02:00
off_policy_algorithm.py Add supported action spaces checks (#254) 2020-12-06 14:05:10 +02:00
on_policy_algorithm.py Add supported action spaces checks (#254) 2020-12-06 14:05:10 +02:00
policies.py Doc fixes and add monitor_kwargs parameter (#230) 2020-11-20 10:28:54 +01:00
preprocessing.py Avoid transposing channel-first envs (#213) 2020-11-03 12:34:09 +01:00
results_plotter.py Cleanup docstring types (#169) 2020-10-02 20:05:55 +03:00
running_mean_std.py Cleanup docstring types (#169) 2020-10-02 20:05:55 +03:00
save_util.py Fix for saving big replay buffer, use pickle protocol>=4 (#239) 2020-11-24 16:13:00 +02:00
torch_layers.py Avoid transposing channel-first envs (#213) 2020-11-03 12:34:09 +01:00
type_aliases.py Doc fixes and add monitor_kwargs parameter (#230) 2020-11-20 10:28:54 +01:00
utils.py Doc fixes and add monitor_kwargs parameter (#230) 2020-11-20 10:28:54 +01:00