Anssi 18d10dbf42 Use Monitor episode reward/length for evaluate_policy (#220) ... * Update evaluate_policy to use monitor data if available * Update documentation * Cleaning up * Remove unnecessary typing trickery * Update doc * Rename is_wrapped to clarify it is for vecenvs * Add is_wrapped for regular envs * Add is_wrapped call for subprocvecenv and update code for circular imports * Move new functions back to env_util and fix imports * Update changelog * Clarify evaluate_policy docs * Add tests for wrapped modifying episode lengths * Fix tests * Update changelog * Minor edits * Add warn switch to evaluate_policy and update tests Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>		2020-11-16 11:52:28 +01:00
..
__init__.py	Use Monitor episode reward/length for evaluate_policy (#220)	2020-11-16 11:52:28 +01:00
base_vec_env.py	Use Monitor episode reward/length for evaluate_policy (#220)	2020-11-16 11:52:28 +01:00
dummy_vec_env.py	Use Monitor episode reward/length for evaluate_policy (#220)	2020-11-16 11:52:28 +01:00
obs_dict_wrapper.py	Implement HER (#120)	2020-10-22 11:56:43 +02:00
subproc_vec_env.py	Use Monitor episode reward/length for evaluate_policy (#220)	2020-11-16 11:52:28 +01:00
util.py	Improve typing coverage (#175)	2020-10-07 10:51:49 +02:00
vec_check_nan.py	Improve typing coverage (#175)	2020-10-07 10:51:49 +02:00
vec_frame_stack.py	Avoid transposing channel-first envs (#213)	2020-11-03 12:34:09 +01:00
vec_normalize.py	Implement HER (#120)	2020-10-22 11:56:43 +02:00
vec_transpose.py	Cleanup docstring types (#169)	2020-10-02 20:05:55 +03:00
vec_video_recorder.py	Improve typing coverage (#175)	2020-10-07 10:51:49 +02:00