Sven Mika
|
e40b14d255
[RLlib] Batch-size for truncate_episode batch_mode should be confgurable in agent-steps (rather than env-steps), if needed. (#12420)
|
3 years ago |
Sven Mika
|
414041c6dd
[RLlib] Do not create env on driver iff num_workers > 0. (#11307)
|
4 years ago |
Sven Mika
|
2746fc0476
[RLlib] Auto-framework, retire `use_pytorch` in favor of `framework=...` (#8520)
|
4 years ago |
Eric Liang
|
dd70720578
[rllib] Rename sample_batch_size => rollout_fragment_length (#7503)
|
4 years ago |
Sven Mika
|
20ef4a8603
[RLlib] Cleanup/unify all test cases. (#7533)
|
4 years ago |
Sven Mika
|
d537e9f0d8
[RLlib] Exploration API: merge deterministic flag with exploration classes (SoftQ and StochasticSampling). (#7155)
|
4 years ago |
Sven Mika
|
6e1c3ea824
[RLlib] Exploration API (+EpsilonGreedy sub-class). (#6974)
|
4 years ago |
Sven
|
60d4d5e1aa
Remove future imports (#6724)
|
4 years ago |
Eric Liang
|
5d7afe8092
[rllib] Try moving RLlib to top level dir (#5324)
|
5 years ago |