ChenDRAG e27b5a26f3

Refactor PG algorithm and change behavior of compute_episodic_return (#319) ...

- simplify code
- apply value normalization (global) and adv norm (per-batch) in on-policy algorithms

2021-03-23 22:05:48 +08:00

..

__init__.py

seealso and change policy dir structure

2020-04-09 21:36:53 +08:00

a2c.py

Refactor PG algorithm and change behavior of compute_episodic_return (#319)

2021-03-23 22:05:48 +08:00

c51.py

fix qvalue mask_action error for obs_next (#310)

2021-03-15 08:06:24 +08:00

ddpg.py

Remap action to fit gym's action space (#313)

2021-03-21 16:45:50 +08:00

discrete_sac.py

Remap action to fit gym's action space (#313)

2021-03-21 16:45:50 +08:00

dqn.py

fix qvalue mask_action error for obs_next (#310)

2021-03-15 08:06:24 +08:00

pg.py

Refactor PG algorithm and change behavior of compute_episodic_return (#319)

2021-03-23 22:05:48 +08:00

ppo.py

Refactor PG algorithm and change behavior of compute_episodic_return (#319)

2021-03-23 22:05:48 +08:00

qrdqn.py

fix qvalue mask_action error for obs_next (#310)

2021-03-15 08:06:24 +08:00

sac.py

Remap action to fit gym's action space (#313)

2021-03-21 16:45:50 +08:00

td3.py

Remap action to fit gym's action space (#313)

2021-03-21 16:45:50 +08:00