.. |
debug
|
827ab91741
[RLlib] Replace remaining mentions of "trainer" by "algorithm". (#36557)
|
1 年之前 |
exploration
|
ad88af2e2e
[RLlib] Remove deprecation warnings in `utils/exploration` directory. (#37404)
|
1 年之前 |
metrics
|
656fe0703c
Revert revert [RLlib] DreamerV3 Main Algo. (#36571)
|
1 年之前 |
pre_checks
|
05eea3844a
[RLlib] Fix `env_check` for parametric actions (with action mask). (#34790)
|
1 年之前 |
replay_buffers
|
656fe0703c
Revert revert [RLlib] DreamerV3 Main Algo. (#36571)
|
1 年之前 |
schedules
|
f1f714c69e
[RLlib] Learner API enhancements and cleanups (prep. for DreamerV3). (#35877)
|
1 年之前 |
spaces
|
6f88b0c674
[RLlib] Bump Gymnasium to 0.28.1 (#35698)
|
1 年之前 |
tests
|
2ffd7e49bd
[rllib] Fix storage-path related tests (#38947)
|
1 年之前 |
__init__.py
|
15318239ba
[RLlib] Unify TensorSpecs to a single framework-agnostic class. (#34493)
|
1 年之前 |
actor_manager.py
|
a794320dff
[RLlib] RLlib light: EnvRunner API. (#35872)
|
1 年之前 |
actors.py
|
0f62ccc6ee
[RLlib] Clean up some deprecation messages (they shouldn't be there) and make others `error=True` (from `error=False`) (#38555)
|
1 年之前 |
annotations.py
|
1c636e7c30
[RLlib] DreamerV3: Learner API classes for tf-keras, loss functions, additional update method. (#35385)
|
1 年之前 |
checkpoints.py
|
821b835238
[train] clean up ray.train._checkpoint imports (#38951)
|
1 年之前 |
compression.py
|
c42b080617
[RLlib] [Tune] [Autoscaler] Remove `six` dependency (#30815)
|
1 年之前 |
deprecation.py
|
684e28b380
[RLlib] RLlib deprecation Notices Part 1 (algorithm/, evaluation/, execution/, models/jax/) (#36826)
|
1 年之前 |
error.py
|
8f55ce695a
[RLlib] Add RLModule and MARLModule Serialize Deserialize methods (#31529)
|
1 年之前 |
filter.py
|
256867b0cf
[RLlib] Add backward compatibility to MeanStdFilter to restore from older checkpoints. (#30439)
|
1 年之前 |
filter_manager.py
|
181330c120
[RLlib] Add config option to enable/disable TO vs FROM worker filter updates (aka filter syncing). (#36204)
|
1 年之前 |
framework.py
|
e399fb8037
[RLlib] APPO+new-stack (Atari benchmark) - Preparatory PR 02. (#34777)
|
1 年之前 |
from_config.py
|
7bd047cd4a
[RLlib] Trainer runner v1 (#31262)
|
1 年之前 |
gym.py
|
3fc2aac975
[RLlib] Auto-detect old gym/gymnasium APIs and wrap accordingly. Configurable. (#31960)
|
1 年之前 |
images.py
|
4963dfaae0
[api] Add API stability annotations for all RLlib symbols and add to LINT (#25060)
|
2 年之前 |
lambda_defaultdict.py
|
2125b18f37
[RLlib][Docs] Enable doctests for RLLib (#35931)
|
1 年之前 |
memory.py
|
199dc8cff0
Revert "Revert "[RLlib] @deprecate(error=True|False) escalation."" (#28807)
|
2 年之前 |
minibatch_utils.py
|
960032a15f
[RLlib][RLModules] RNNs and RLModules (#32723)
|
1 年之前 |
nested_dict.py
|
960032a15f
[RLlib][RLModules] RNNs and RLModules (#32723)
|
1 年之前 |
numpy.py
|
b0045799e3
[RLlib] DreamerV3: Make 200M (XL model) work; mixed float16 option (#38461)
|
1 年之前 |
policy.py
|
0f62ccc6ee
[RLlib] Clean up some deprecation messages (they shouldn't be there) and make others `error=True` (from `error=False`) (#38555)
|
1 年之前 |
serialization.py
|
dd4819fc92
[RLlib] Fix multibinary space serialization (#34762)
|
1 年之前 |
sgd.py
|
acf2bf9b2f
[RLlib] Get rid of all these deprecation warnings. (#27085)
|
2 年之前 |
tensor_dtype.py
|
960032a15f
[RLlib][RLModules] RNNs and RLModules (#32723)
|
1 年之前 |
test_utils.py
|
2d0544bc73
[train/tune] Remove save_to_object/restore_from_object (#38757)
|
1 年之前 |
tf_run_builder.py
|
d28552b7b6
[RLlib] Fix tf timeline in ray local mode. (#31139)
|
1 年之前 |
tf_utils.py
|
b0045799e3
[RLlib] DreamerV3: Make 200M (XL model) work; mixed float16 option (#38461)
|
1 年之前 |
threading.py
|
4963dfaae0
[api] Add API stability annotations for all RLlib symbols and add to LINT (#25060)
|
2 年之前 |
timer.py
|
199dc8cff0
Revert "Revert "[RLlib] @deprecate(error=True|False) escalation."" (#28807)
|
2 年之前 |
torch_utils.py
|
960032a15f
[RLlib][RLModules] RNNs and RLModules (#32723)
|
1 年之前 |
typing.py
|
827ab91741
[RLlib] Replace remaining mentions of "trainer" by "algorithm". (#36557)
|
1 年之前 |
window_stat.py
|
199dc8cff0
Revert "Revert "[RLlib] @deprecate(error=True|False) escalation."" (#28807)
|
2 年之前 |