stable-baselines3-contrib-sacd/sb3_contrib
Honglu Fan cad9034fdb
Handle batch norm in target update (#99)
* Copy running stats regardless of tau in QRDQN and TQC. See https://github.com/DLR-RM/stable-baselines3/issues/996

* Copy running stats regardless of tau in QRDQN and TQC. See https://github.com/DLR-RM/stable-baselines3/issues/996

* Copy running stats regardless of tau in QRDQN and TQC. See https://github.com/DLR-RM/stable-baselines3/issues/996

* roll back test_cnn.py
2022-08-27 12:31:00 +02:00
..
ars Use higher resolution time_ns() and avoid division by zero (#91) 2022-07-25 23:12:20 +02:00
common Support `device="auto"`for buffers and set it as default value (#98) 2022-08-24 09:48:18 +02:00
ppo_mask Fixed missing verbose parameter passing (#97) 2022-08-16 15:54:46 +02:00
ppo_recurrent Fixed shared_lstm argument in CNN and MultiInput Policies for RecurrentPPO (#90) 2022-07-26 00:27:17 +02:00
qrdqn Handle batch norm in target update (#99) 2022-08-27 12:31:00 +02:00
tqc Handle batch norm in target update (#99) 2022-08-27 12:31:00 +02:00
trpo Release v1.6.0 and bug fix for TRPO (#84) 2022-07-12 23:12:24 +02:00
__init__.py Recurrent PPO (#53) 2022-05-30 04:31:12 +02:00
py.typed
version.txt Maskable eval callback call callback fix (#93) 2022-07-27 19:52:07 +02:00