Max Lodel fc68af8841 Fixed shared_lstm argument in CNN and MultiInput Policies for RecurrentPPO (#90) ... * fixed shared_lstm parameter in CNN and MultiInput Policies * updated tests * changelog * Fix FPS for recurrent PPO * Fix import * Update changelog Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>		2022-07-26 00:27:17 +02:00
..
wrappers	Upgrade Gym to 0.21 (#59)	2022-02-22 16:25:43 +01:00
test_cnn.py	Add Trust Region Policy Optimization (TRPO) (#40)	2021-12-29 11:58:03 +01:00
test_deterministic.py	Recurrent PPO (#53)	2022-05-30 04:31:12 +02:00
test_dict_env.py	Add Trust Region Policy Optimization (TRPO) (#40)	2021-12-29 11:58:03 +01:00
test_distributions.py	Upgrade Gym to 0.21 (#59)	2022-02-22 16:25:43 +01:00
test_identity.py	Release v1.6.0 and bug fix for TRPO (#84)	2022-07-12 23:12:24 +02:00
test_invalid_actions.py	Update Maskable PPO to match SB3 PPO + improve coverage (#56)	2021-12-10 12:48:19 +01:00
test_lstm.py	Fixed shared_lstm argument in CNN and MultiInput Policies for RecurrentPPO (#90)	2022-07-26 00:27:17 +02:00
test_run.py	Allow PPO to turn off advantage normalization (#61)	2022-02-23 10:11:16 +01:00
test_save_load.py	Upgrade to python 3.7+ syntax (#69)	2022-04-25 13:02:07 +02:00
test_train_eval_mode.py	Upgrade to python 3.7+ syntax (#69)	2022-04-25 13:02:07 +02:00
test_utils.py	Upgrade Gym to 0.21 (#59)	2022-02-22 16:25:43 +01:00