Yi Su df35718992

Implement TD3+BC for offline RL (#660) ...

- implement TD3+BC for offline RL;
- fix a bug in trainer about test reward not logged because self.env_step is not set for offline setting;

2022-06-07 00:39:37 +08:00

..

__init__.py

Implement BCQPolicy and offline_bcq example (#480)

2021-11-22 22:21:02 +08:00

expert_QRDQN_CartPole-v0.pkl

make unit test faster (#522)

2022-02-09 00:24:52 +08:00

expert_SAC_Pendulum-v1.pkl

upgrade gym version to >=0.21, fix related CI and update examples/atari (#534)

2022-02-25 07:40:33 +08:00

gather_cartpole_data.py

rename save_fn to save_best_fn to avoid ambiguity (#575)

2022-03-22 04:29:27 +08:00

gather_pendulum_data.py

rename save_fn to save_best_fn to avoid ambiguity (#575)

2022-03-22 04:29:27 +08:00

test_bcq.py

Add show_progress option for trainer (#641)

2022-05-17 23:41:59 +08:00

test_cql.py

rename save_fn to save_best_fn to avoid ambiguity (#575)

2022-03-22 04:29:27 +08:00

test_discrete_bcq.py

Fix save_checkpoint_fn return value (#659)

2022-06-03 01:07:07 +08:00

test_discrete_cql.py

rename save_fn to save_best_fn to avoid ambiguity (#575)

2022-03-22 04:29:27 +08:00

test_discrete_crr.py

rename save_fn to save_best_fn to avoid ambiguity (#575)

2022-03-22 04:29:27 +08:00

test_gail.py

Fix save_checkpoint_fn return value (#659)

2022-06-03 01:07:07 +08:00

test_td3_bc.py

Implement TD3+BC for offline RL (#660)

2022-06-07 00:39:37 +08:00