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

..

imitation

Remove reward_normaliztion option in offpolicy algorithm (#298)

2021-02-27 11:20:43 +08:00

modelbase

Remove reward_normaliztion option in offpolicy algorithm (#298)

2021-02-27 11:20:43 +08:00

modelfree

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

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

multiagent

Step collector implementation (#280)

2021-02-19 10:33:49 +08:00

__init__.py

Step collector implementation (#280)

2021-02-19 10:33:49 +08:00

base.py

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

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

random.py

Trainer refactor : some definition change (#293)

2021-02-21 13:06:02 +08:00