.. |
exploration
|
e485aa846a
[RLlib; Docs overhaul] Overhaul of auto-API reference pages (via sphinx autoclass/automodule). (#19786)
|
2 years ago |
metrics
|
62dbf26394
[RLlib] POC: Run PGTrainer w/o the distr. exec API (Trainer's new training_iteration method). (#20984)
|
2 years ago |
pre_checks
|
12b087acb8
[RLlib] Base env pre-checker. (#21569)
|
2 years ago |
schedules
|
e485aa846a
[RLlib; Docs overhaul] Overhaul of auto-API reference pages (via sphinx autoclass/automodule). (#19786)
|
2 years ago |
spaces
|
35af30a446
[RLlib] Issue 21109: Action unsquashing causes inf/NaN actions for unbounded action spaces. (#21110)
|
2 years ago |
tests
|
12b087acb8
[RLlib] Base env pre-checker. (#21569)
|
2 years ago |
__init__.py
|
f94bd99ce4
[RLlib] Issue 21044: Improve error message for "multiagent" dict checks. (#21448)
|
2 years ago |
actors.py
|
90c6b10498
[RLlib] Decentralized multi-agent learning; PR #01 (#21421)
|
2 years ago |
annotations.py
|
e485aa846a
[RLlib; Docs overhaul] Overhaul of auto-API reference pages (via sphinx autoclass/automodule). (#19786)
|
2 years ago |
compression.py
|
b804d40c04
Stop vendoring pyarrow (#7233)
|
4 years ago |
debug.py
|
92f030331e
[RLlib] Initial code/comment cleanups in preparation for decentralized multi-agent learner. (#21420)
|
2 years ago |
deprecation.py
|
e485aa846a
[RLlib; Docs overhaul] Overhaul of auto-API reference pages (via sphinx autoclass/automodule). (#19786)
|
2 years ago |
error.py
|
026bf01071
[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535)
|
3 years ago |
filter.py
|
daa4304a91
[RLlib] Switch off preprocessors by default for PGTrainer. (#21008)
|
2 years ago |
filter_manager.py
|
9a83908c46
[rllib] Deprecate policy optimizers (#8345)
|
4 years ago |
framework.py
|
cf21c634a3
[RLlib] Fix deprecated warning for torch_ops.py (soft-replaced by torch_utils.py). (#19982)
|
3 years ago |
from_config.py
|
3f89f35e52
[RLlib] Better error messages and hints; + failure-mode tests; (#18466)
|
3 years ago |
images.py
|
05c9dfbbda
[RLlib] CV2 to Skimage dependency change (#16841)
|
3 years ago |
install_atari_roms.sh
|
ac5d255c9c
[rllib/docker] silent unzip of atari roms (#18340)
|
3 years ago |
memory.py
|
0b308719f8
[RLlib; Docs overhaul] Docstring cleanup: rllib/utils (#19829)
|
3 years ago |
numpy.py
|
9e6b871739
[RLlib] Better utils for flattening complex inputs and enable prev-actions for LSTM/attention for complex action spaces. (#21330)
|
2 years ago |
sgd.py
|
853d10871c
[RLlib] Issue 18499: PGTrainer with training_iteration fn does not support multi-GPU. (#21376)
|
2 years ago |
test_utils.py
|
7517aefe05
[RLlib] Bring back BC and Marwil learning tests. (#21574)
|
2 years ago |
tf_ops.py
|
9e6b871739
[RLlib] Better utils for flattening complex inputs and enable prev-actions for LSTM/attention for complex action spaces. (#21330)
|
2 years ago |
tf_run_builder.py
|
7588bfd315
[Lint] Add flake8-bugbear (#19053)
|
3 years ago |
tf_utils.py
|
92f030331e
[RLlib] Initial code/comment cleanups in preparation for decentralized multi-agent learner. (#21420)
|
2 years ago |
threading.py
|
0b308719f8
[RLlib; Docs overhaul] Docstring cleanup: rllib/utils (#19829)
|
3 years ago |
timer.py
|
3c6b94f3f5
[rllib] Enable performance metrics reporting for RLlib pipelines, add A3C (#7299)
|
4 years ago |
torch_ops.py
|
9e6b871739
[RLlib] Better utils for flattening complex inputs and enable prev-actions for LSTM/attention for complex action spaces. (#21330)
|
2 years ago |
torch_utils.py
|
92f030331e
[RLlib] Initial code/comment cleanups in preparation for decentralized multi-agent learner. (#21420)
|
2 years ago |
typing.py
|
d5bfb7b7da
[RLlib] Preparatory PR for multi-agent multi-GPU learner (alpha-star style) #03 (#21652)
|
2 years ago |
window_stat.py
|
0b308719f8
[RLlib; Docs overhaul] Docstring cleanup: rllib/utils (#19829)
|
3 years ago |