Sven Mika
|
49cd7ea6f9
[RLlib] Trainer sub-class PPO/DDPPO (instead of `build_trainer()`). (#20571)
|
2 years ago |
Sven Mika
|
d001af3e59
[RLlib] Allow `rllib rollout` to run distributed via evaluation workers. (#13718)
|
3 years ago |
Sven Mika
|
d14b501692
[RLlib] First attempt at cleaning up algo code in RLlib: PG. (#10115)
|
4 years ago |
Richard Liaw
|
d35f0e40d0
[tune] Use public methods for trainable (#9184)
|
4 years ago |
Sven Mika
|
368088be85
[RLlib] Sample batch docs and cleanup. (#8778)
|
4 years ago |
Sven
|
60d4d5e1aa
Remove future imports (#6724)
|
4 years ago |
Robert Nishihara
|
480206eef8
Remove some Python 2 compatibility code. (#6624)
|
4 years ago |
Siyuan (Ryans) Zhuang
|
f48293f96d
Fix deprecated warning (#6142)
|
5 years ago |
Wonseok Jeon
|
281829e712
MADDPG implementation in RLlib (#5348)
|
5 years ago |
Eric Liang
|
5d7afe8092
[rllib] Try moving RLlib to top level dir (#5324)
|
5 years ago |