Sven Mika
|
d5bfb7b7da
[RLlib] Preparatory PR for multi-agent multi-GPU learner (alpha-star style) #03 (#21652)
|
2 years ago |
Sven Mika
|
b10d5533be
[RLlib] Issue 20920 (partial solution): contrib/MADDPG + pettingzoo coop-pong-v4 not working. (#21452)
|
2 years ago |
Sven Mika
|
60b2219d72
[RLlib] Allow for evaluation to run by `timesteps` (alternative to `episodes`) and add auto-setting to make sure train doesn't ever have to wait for eval (e.g. long episodes) to finish. (#20757)
|
2 years ago |
Sven Mika
|
9e38f6f613
[RLlib] Trainer sub-class DDPG/TD3/APEX-DDPG (instead of `build_trainer`). (#20636)
|
2 years ago |
Artur Niederfahrenhorst
|
d07e50e957
[RLlib] Replay buffer API (cleanups; docstrings; renames; move into `rllib/execution/buffers` dir) (#20552)
|
2 years ago |
gjoliver
|
d81885c1f1
[RLlib] Fix all the CI tests that were broken by is_training and replay buffer changes; re-comment-in the failing RLlib tests (#19809)
|
3 years ago |
Sven Mika
|
4888d7c9af
[RLlib] Replay buffers: Add config option to store contents in checkpoints. (#17999)
|
3 years ago |
Sven Mika
|
b6aa8223bc
[RLlib] Fix `final_scale`'s default value to 0.02 (see OrnsteinUhlenbeck exploration). (#18070)
|
3 years ago |
Thomas Lecat
|
c02f91fa2d
[RLlib] Ape-X doesn't take the value of `prioritized_replay` into account (#17541)
|
3 years ago |
Sven Mika
|
c2ea2c01bb
[RLlib] Redo: Add support for multi-GPU to DDPG. (#17789)
|
3 years ago |
Amog Kamsetty
|
0b8489dcc6
Revert "[RLlib] Add support for multi-GPU to DDPG. (#17586)" (#17707)
|
3 years ago |
Sven Mika
|
0eb0e0ff58
[RLlib] Add support for multi-GPU to DDPG. (#17586)
|
3 years ago |
Sven Mika
|
90b21ce27e
[RLlib] De-flake 3 test cases; Fix `config.simple_optimizer` and `SampleBatch.is_training` warnings. (#17321)
|
3 years ago |
Sven Mika
|
1fd0eb805e
[RLlib] Redo fix bug normalize vs unsquash actions (original PR made log-likelihood test flakey). (#17014)
|
3 years ago |
Amog Kamsetty
|
bc33dc7e96
Revert "[RLlib] Fix bug in policy.py: normalize_actions=True has to call `unsquash_action`, not `normalize_action`." (#17002)
|
3 years ago |
Sven Mika
|
7862dd64ea
[RLlib] Fix bug in policy.py: normalize_actions=True has to call `unsquash_action`, not `normalize_action`. (#16774)
|
3 years ago |
Michael Luo
|
474f04e322
[RLlib] DDPG/TD3 + A3C/A2C + MARWIL/BC Annotation/Comments/Code Cleanup (#14707)
|
3 years ago |
Sven Mika
|
4f66309e19
[RLlib] Redo issue 14533 tf enable eager exec (#14984)
|
3 years ago |
SangBin Cho
|
fa5f961d5e
Revert "[RLlib] Issue 14533: `tf.enable_eager_execution()` must be called at beginning. (#14737)" (#14918)
|
3 years ago |
Sven Mika
|
3e389d5812
[RLlib] Issue 14533: `tf.enable_eager_execution()` must be called at beginning. (#14737)
|
3 years ago |
Sven Mika
|
732197e23a
[RLlib] Multi-GPU for tf-DQN/PG/A2C. (#13393)
|
3 years ago |
Sven Mika
|
19c8033df2
[RLlib] Fix most remaining RLlib algos for running with trajectory view API. (#12366)
|
3 years ago |
Sven Mika
|
b6b54f1c81
[RLlib] Trajectory view API: enable by default for SAC, DDPG, DQN, SimpleQ (#11827)
|
3 years ago |
Sven Mika
|
28ab797cf5
[RLlib] Deprecate old classes, methods, functions, config keys (in prep for RLlib 1.0). (#10544)
|
4 years ago |
Sven Mika
|
4da0e542d5
[RLlib] DDPG and SAC eager support (preparation for tf2.x) (#9204)
|
4 years ago |
Piotr Januszewski
|
155cc81e40
Clarify training intensity configuration docstring (#9244) (#9306)
|
4 years ago |
Sven Mika
|
4fd8977eaf
[RLlib] Minor cleanup in preparation to tf2.x support. (#9130)
|
4 years ago |
Sven Mika
|
2746fc0476
[RLlib] Auto-framework, retire `use_pytorch` in favor of `framework=...` (#8520)
|
4 years ago |
Eric Liang
|
aa7a58e92f
[rllib] Support training intensity for dqn / apex (#8396)
|
4 years ago |
Sven Mika
|
d0fab84e4d
[RLlib] DDPG PyTorch version. (#7953)
|
4 years ago |