Sven Mika
|
3d063438c3
[RLlib] Deprecate `get_algorithm_class()`. (#30053)
|
1 年之前 |
Sven Mika
|
432f023642
[RLlib] Deprecate `AlgorithmConfig.framework("tfe")`: Use `tf2` instead. (#29755)
|
2 年之前 |
Sven Mika
|
b218ae7e4a
[RLlib] Replace CartPole-v0 -> CartPole-v1 everywhere, incl. docs. (#29752)
|
2 年之前 |
Sven Mika
|
42864d711d
[RLlib; AIR; Tune] Replace all remaining `tune.run()` with `tune.Tuner(...).fit()`. (#28325)
|
2 年之前 |
Artur Niederfahrenhorst
|
0dceddb912
[RLlib] Move learning_starts logic from buffers into `training_step()`. (#26032)
|
2 年之前 |
Sven Mika
|
130b7eeaba
[RLlib] `Trainer` to `Algorithm` renaming. (#25539)
|
2 年之前 |
Sven Mika
|
7c39aa5fac
[RLlib] Trainer.training_iteration -> Trainer.training_step; Iterations vs reportings: Clarification of terms. (#25076)
|
2 年之前 |
Artur Niederfahrenhorst
|
fb2915d26a
[RLlib] Replay Buffer API and Ape-X. (#24506)
|
2 年之前 |
Sven Mika
|
f066180ed5
[RLlib] Deprecate `timesteps_per_iteration` config key (in favor of `min_[sample|train]_timesteps_per_reporting`. (#24372)
|
2 年之前 |
Balaji Veeramani
|
7f1bacc7dc
[CI] Format Python code with Black (#21975)
|
2 年之前 |
Sven Mika
|
d5bfb7b7da
[RLlib] Preparatory PR for multi-agent multi-GPU learner (alpha-star style) #03 (#21652)
|
2 年之前 |
Avnish Narayan
|
026bf01071
[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535)
|
3 年之前 |
Sven Mika
|
d001af3e59
[RLlib] Allow `rllib rollout` to run distributed via evaluation workers. (#13718)
|
3 年之前 |
Barak Michener
|
8e76796fd0
ci: Redo `format.sh --all` script & backfill lint fixes (#9956)
|
4 年之前 |
Sven Mika
|
fcdf410ae1
[RLlib] Tf2.x native. (#8752)
|
4 年之前 |
Sven Mika
|
4da0e542d5
[RLlib] DDPG and SAC eager support (preparation for tf2.x) (#9204)
|
4 年之前 |
Sven Mika
|
2746fc0476
[RLlib] Auto-framework, retire `use_pytorch` in favor of `framework=...` (#8520)
|
4 年之前 |
Sven Mika
|
e4bd5db4d8
[RLlib] Minimal ParamNoise PR. (#7772)
|
4 年之前 |
Sven Mika
|
20ef4a8603
[RLlib] Cleanup/unify all test cases. (#7533)
|
4 年之前 |
Sven Mika
|
510c850651
[RLlib] SAC add discrete action support. (#7320)
|
4 年之前 |
Eric Liang
|
1660b52751
[rllib] Fix torch GPU / yaml load warning (#7278)
|
4 年之前 |
Sven Mika
|
0db2046b0a
[RLlib] Policy.compute_log_likelihoods() and SAC refactor. (issue #7107) (#7124)
|
4 年之前 |
Sven Mika
|
5ac5ac9560
[RLlib] Fix broken example: tf-eager with custom-RNN (#6732). (#7021)
|
4 年之前 |
Michael Luo
|
548df014ec
SAC Performance Fixes (#6295)
|
4 年之前 |
Eric Liang
|
be5dd8eb5e
Enable direct calls by default (#6367)
|
4 年之前 |
Eric Liang
|
a0dcb45dc3
[rllib] Fix APEX priorities returning zero all the time (#5980)
|
5 年之前 |
gehring
|
8903bcd0c3
[rllib] Tracing for eager tensorflow policies with `tf.function` (#5705)
|
5 年之前 |
Eric Liang
|
19bbf1eb4d
[rllib] Revert [rllib] Port DDPG to the build_tf_policy pattern (#5626)
|
5 年之前 |
gehring
|
b520f6141e
[rllib] Adds eager support with a generic `TFEagerPolicy` class (#5436)
|
5 年之前 |