Sven Mika 8c28fe265a [RLlib] Cleanup examples folder vol. 23: Add example script for custom metrics on `EnvRunners` (using `MetricsLogger` API). (#47969) 2 天之前
..
debug 710f557308 [RLlib] Cleanup, rename, clarify: Algorithm.workers/evaluation_workers, local_worker(), etc.. (#46726) 3 月之前
exploration c9fa046438 [RLlib] Discontinue support for "hybrid" API stack (using RLModule + Learner, but still on RolloutWorker and Policy) (#46085) 3 周之前
metrics 8c28fe265a [RLlib] Cleanup examples folder vol. 23: Add example script for custom metrics on `EnvRunners` (using `MetricsLogger` API). (#47969) 2 天之前
postprocessing d1f21a5790 [RLlib] Remove 2nd Learner ConnectorV2 pass from PPO (add new GAE Connector piece). Fix: "State-connector" would use `seq_len=20`. (#47401) 1 月之前
pre_checks e07594e665 [RLlib] MultiAgentEnv API enhancements (related to defining obs-/action spaces for agents). (#47830) 3 周之前
replay_buffers e07594e665 [RLlib] MultiAgentEnv API enhancements (related to defining obs-/action spaces for agents). (#47830) 3 周之前
schedules 742f288ab2 [RLlib] Remove `framework_iterator` from codebase. (#47259) 2 月之前
spaces f568674d78 [RLlib] Fix assertion in `Simplex` space. (#47880) 2 周之前
tests f568674d78 [RLlib] Fix assertion in `Simplex` space. (#47880) 2 周之前
__init__.py 742f288ab2 [RLlib] Remove `framework_iterator` from codebase. (#47259) 2 月之前
actor_manager.py e0bcdd4cff [RLlib; fault-tolerance] Fix spot node preemption problem (RLlib does not catch correct `ObjectLostError`). (#47940) 1 周之前
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 e182e192c1 [RLlib] New API stack: (Multi)RLModule overhaul vol 03 (Introduce generic `_forward` to further simplify the user experience). (#47889) 2 周之前
checkpoints.py a6cf9d7d9b [RLlib] Enable cloud checkpointing. (#47682) 3 周之前
compression.py c42b080617 [RLlib] [Tune] [Autoscaler] Remove `six` dependency (#30815) 1 年之前
deprecation.py 887eddd924 [RLlib] Updating codeblocks in RLlib part 1 (#37271) 1 年之前
error.py 5c00c92e3b [RLlib] Remove CLI from docs (soon to be deprecated and replaced by python API). (#46724) 3 月之前
filter.py eebfdc2148 [RLlib; docs] New API stack migration guide. (#47779) 3 周之前
filter_manager.py 710f557308 [RLlib] Cleanup, rename, clarify: Algorithm.workers/evaluation_workers, local_worker(), etc.. (#46726) 3 月之前
framework.py 2a8b1225b2 [RLlib] RLModule: Add `TargetNetworkAPI` and implement for APPO and SAC. (#46656) 3 月之前
from_config.py 887eddd924 [RLlib] Updating codeblocks in RLlib part 1 (#37271) 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 ed5b3821b2 [RLlib] Add "shuffle batch per epoch" option. (#47458) 1 月之前
numpy.py 0ec68e2cc1 [RLlib] ConnectorV2: Cleanups and API enhancements. (#43040) 8 月之前
policy.py 8a7960fc70 [RLlib] Add more detailed options to `Algorithm.add_module/remove_module`. (#46836) 2 月之前
serialization.py a62d4bfd3a [RLlib] New API stack: (Multi)RLModule overhaul vol 04 (deprecate RLModuleConfig; cleanups, DefaultModelConfig dataclass). (#47908) 1 周之前
sgd.py 7b407c68ad [RLlib] Introduce `OldAPIStack` decorator; Do-over of all API decorators (in particular for new API stack classes). (#43657) 7 月之前
tensor_dtype.py 960032a15f [RLlib][RLModules] RNNs and RLModules (#32723) 1 年之前
test_utils.py 616eef8f8a [RLlib] New API stack: (Multi)RLModule overhaul vol 05 (deprecate Specs, SpecDict, TensorSpec). (#47915) 1 周之前
tf_run_builder.py 7b407c68ad [RLlib] Introduce `OldAPIStack` decorator; Do-over of all API decorators (in particular for new API stack classes). (#43657) 7 月之前
tf_utils.py 3862ab560c [RLlib] APPO on new API stack (w/ EnvRunners). (#46216) 3 月之前
threading.py 7b407c68ad [RLlib] Introduce `OldAPIStack` decorator; Do-over of all API decorators (in particular for new API stack classes). (#43657) 7 月之前
torch_utils.py 6a62b0fc06 [RLlib] Add gradient logging as default. (#47451) 1 月之前
typing.py a62d4bfd3a [RLlib] New API stack: (Multi)RLModule overhaul vol 04 (deprecate RLModuleConfig; cleanups, DefaultModelConfig dataclass). (#47908) 1 周之前