n+e 140b1c2cab

Improve PER (#159) ...

- use segment tree to rewrite the previous PrioReplayBuffer code, add the test

- enable all Q-learning algorithms to use PER

2020-08-06 10:26:24 +08:00

..

data

Improve PER (#159)

2020-08-06 10:26:24 +08:00

env

ShmemVectorEnv Implementation (#174)

2020-08-04 13:39:05 +08:00

exploration

Add auto alpha tuning and exploration noise for sac. (#80)

2020-06-16 22:17:28 +08:00

policy

Improve PER (#159)

2020-08-06 10:26:24 +08:00

trainer

doc update and do not force save 'policy' in np format (#168)

2020-07-27 16:54:14 +08:00

utils

use nn.Sequential in DQN (#176)

2020-08-02 15:14:44 +08:00

__init__.py

docs fix and v0.2.5 (#156)

2020-07-22 14:42:08 +08:00