Avnish Narayan
|
684e28b380
[RLlib] RLlib deprecation Notices Part 1 (algorithm/, evaluation/, execution/, models/jax/) (#36826)
|
1 年之前 |
Artur Niederfahrenhorst
|
8a9a176a24
[RLlib] Remove all default config objects and rllib/agents (#33242)
|
1 年之前 |
Cade Daniel
|
e54ff46b62
[Fail on pytest warnings 1/n] Marking strings with invalid escape sequences as raw strings (#31523)
|
1 年之前 |
Max Pumperla
|
23f460b0fe
[RLlib] AlgorithmConfig docs (#29796)
|
1 年之前 |
Sven Mika
|
087548031b
[RLlib] AlgorithmConfigs: Make None a valid value for methods to set properties; Use new `NotProvided` singleton, instead, to indicate no changes wanted on that property. (#30020)
|
1 年之前 |
Sven Mika
|
2ed09c5445
[RLlib] Move all config validation logic into AlgorithmConfig classes. (#29854)
|
1 年之前 |
Sven Mika
|
5af66e66cc
[RLlib] AlgorithmConfigs: Broad rollout; Example scripts. (#29700)
|
2 年之前 |
Sven Mika
|
53674b6b78
[RLlib] Set default `num_rollout_workers` in AlgorithmConfig to 0. Also fixes SAC, DDPG, CQL wrong default setups! (#29546)
|
2 年之前 |
Sven Mika
|
e7a614f388
Revert "Revert "[RLlib] AlgorithmConfig: Next steps (volume 01); Algos, Rollo…" (#29747)
|
2 年之前 |
Kai Fricke
|
12b579d95e
Revert "[RLlib] AlgorithmConfig: Next steps (volume 01); Algos, RolloutWorker, PolicyMap, WorkerSet use AlgorithmConfig objects under the hood. (#29395)" (#29742)
|
2 年之前 |
Sven Mika
|
182744bbd1
[RLlib] AlgorithmConfig: Next steps (volume 01); Algos, RolloutWorker, PolicyMap, WorkerSet use AlgorithmConfig objects under the hood. (#29395)
|
2 年之前 |
Sven Mika
|
199dc8cff0
Revert "Revert "[RLlib] @deprecate(error=True|False) escalation."" (#28807)
|
2 年之前 |
Amog Kamsetty
|
e501654925
Revert "[RLlib] @deprecate(error=True|False) escalation. (#28733)" (#28795)
|
2 年之前 |
Sven Mika
|
c4348c1889
[RLlib] @deprecate(error=True|False) escalation. (#28733)
|
2 年之前 |
Sven Mika
|
42864d711d
[RLlib; AIR; Tune] Replace all remaining `tune.run()` with `tune.Tuner(...).fit()`. (#28325)
|
2 年之前 |
Sven Mika
|
96693055bd
[RLlib] More Trainer -> Algorithm renaming cleanups. (#25869)
|
2 年之前 |
Sven Mika
|
130b7eeaba
[RLlib] `Trainer` to `Algorithm` renaming. (#25539)
|
2 年之前 |
Artur Niederfahrenhorst
|
94d6c212df
[RLlib] Replay Buffer API documentation. (#24683)
|
2 年之前 |
Artur Niederfahrenhorst
|
35bd397181
[RLlib] Better default values for `training_intensity` and `target_network_update_freq` for R2D2. (#25510)
|
2 年之前 |
Sven Mika
|
b5bc2b93c3
[RLlib] Move all remaining algos into `algorithms` directory. (#25366)
|
2 年之前 |