Sven Mika
|
8ea1bc5ff9
[RLlib] Allow for more than 2^31 policy timesteps. (#11301)
|
4 years ago |
Sven Mika
|
f43d934817
[RLlib] Type annotations for policy. (#9248)
|
4 years ago |
Sven Mika
|
43043ee4d5
[RLlib] Tf2x preparation; part 2 (upgrading `try_import_tf()`). (#9136)
|
4 years ago |
Sven Mika
|
baa053496a
[RLlib] Benchmark and regression test yaml cleanup and restructuring. (#8414)
|
4 years ago |
Sven Mika
|
6c2b9a4cfa
[RLlib] Remove tf.py_function from all Schedule classes (not differentiable and causes other bugs in MA setups). (#8304)
|
4 years ago |
Eric Liang
|
be48e1964b
[rllib] Fix per-worker exploration in Ape-X; make more kwargs required for future safety (#7504)
|
4 years ago |
Sven Mika
|
83e06cd30a
[RLlib] DDPG refactor and Exploration API action noise classes. (#7314)
|
4 years ago |
Sven Mika
|
6e1c3ea824
[RLlib] Exploration API (+EpsilonGreedy sub-class). (#6974)
|
4 years ago |
Sven Mika
|
136ada5fb9
[RLlib] Experiment with py_func as a means to further unify tf and torch (Schedule classes). (#6951)
|
4 years ago |
Sven Mika
|
4c97348cb6
[RLlib] Schedule-classes multi-framework support. (#6926)
|
4 years ago |