| .. |
|
exploration
|
fix(rllib): allow explore=False with tuple action distributions (#10443)
|
2020-09-10 15:03:02 -07:00 |
|
schedules
|
[RLlib] Rename rllib.utils.types into typing to match built-in python module's name. (#10114)
|
2020-08-15 13:24:22 +02:00 |
|
spaces
|
[RLlib] Curiosity minor fixes, do-overs, and testing. (#10143)
|
2020-08-19 17:49:50 +02:00 |
|
tests
|
Change Python's ObjectID to ObjectRef (#9353)
|
2020-07-10 17:49:04 +08:00 |
|
__init__.py
|
[RLlib] Deprecate old classes, methods, functions, config keys (in prep for RLlib 1.0). (#10544)
|
2020-09-06 10:58:00 +02:00 |
|
actors.py
|
Change Python's ObjectID to ObjectRef (#9353)
|
2020-07-10 17:49:04 +08:00 |
|
annotations.py
|
[rllib] Deprecate policy optimizers (#8345)
|
2020-05-21 10:16:18 -07:00 |
|
compression.py
|
Stop vendoring pyarrow (#7233)
|
2020-02-19 19:01:26 -08:00 |
|
debug.py
|
[rllib] Flexible multi-agent replay modes and replay_sequence_length (#8893)
|
2020-06-12 20:17:27 -07:00 |
|
deprecation.py
|
[RLlib] Exploration API: merge deterministic flag with exploration classes (SoftQ and StochasticSampling). (#7155)
|
2020-02-19 12:18:45 -08:00 |
|
error.py
|
Remove future imports (#6724)
|
2020-01-09 00:15:48 -08:00 |
|
filter.py
|
Remove future imports (#6724)
|
2020-01-09 00:15:48 -08:00 |
|
filter_manager.py
|
[rllib] Deprecate policy optimizers (#8345)
|
2020-05-21 10:16:18 -07:00 |
|
framework.py
|
[RLlib] Curiosity enhancements. (#10373)
|
2020-09-05 13:14:24 +02:00 |
|
from_config.py
|
[RLlib] Make envs specifiable in configs by their class path. (#8750)
|
2020-06-03 08:14:29 +02:00 |
|
memory.py
|
[RLlib] Trajectory View API (preparatory cleanup and enhancements). (#9678)
|
2020-07-29 21:15:09 +02:00 |
|
numpy.py
|
[RLlib] Layout of Trajectory View API (new class: Trajectory; not used yet). (#9269)
|
2020-07-14 04:27:49 +02:00 |
|
sgd.py
|
[RLlib] Trajectory view API - 03 Fast LSTM + prev actions/rewards (#9950)
|
2020-08-21 12:35:16 +02:00 |
|
test_utils.py
|
ci: Redo format.sh --all script & backfill lint fixes (#9956)
|
2020-08-07 16:49:49 -07:00 |
|
tf_ops.py
|
ci: Redo format.sh --all script & backfill lint fixes (#9956)
|
2020-08-07 16:49:49 -07:00 |
|
tf_run_builder.py
|
[RLlib] Tf2x preparation; part 2 (upgrading try_import_tf()). (#9136)
|
2020-06-30 10:13:20 +02:00 |
|
timer.py
|
[rllib] Enable performance metrics reporting for RLlib pipelines, add A3C (#7299)
|
2020-02-28 16:44:17 -08:00 |
|
torch_ops.py
|
[RLlib] Curiosity enhancements. (#10373)
|
2020-09-05 13:14:24 +02:00 |
|
tracking_dict.py
|
This PR fixes the currently broken lstm_use_prev_action_reward flag for default lstm models (model.use_lstm=True). (#8970)
|
2020-06-27 20:50:01 +02:00 |
|
typing.py
|
[RLlib] Trajectory view API - 03 Fast LSTM + prev actions/rewards (#9950)
|
2020-08-21 12:35:16 +02:00 |
|
window_stat.py
|
[RLLib] WindowStat bug fix (#9213)
|
2020-07-12 23:01:32 +02:00 |
