xwjiang2010 cdf70c2900 [Tune] Remove legacy resources implementations in Runner and Executor. (#19773) | 2 年之前 | |
---|---|---|
.. | ||
agents | 246787cdd9 Revert "[RLlib] POC: `PGTrainer` class that works by sub-classing, not `trainer_template.py`. (#20055)" (#20284) | 2 年之前 |
contrib | 026bf01071 [RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535) | 3 年之前 |
env | 026bf01071 [RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535) | 3 年之前 |
evaluation | 70fe25055a [RLlib] Issue: Get single step input dict incorrect. (#20217) | 2 年之前 |
examples | cdf70c2900 [Tune] Remove legacy resources implementations in Runner and Executor. (#19773) | 2 年之前 |
execution | a931076f59 [RLlib] Tf2 + eager-tracing same speed as framework=tf; Add more test coverage for tf2+tracing. (#19981) | 3 年之前 |
models | a931076f59 [RLlib] Tf2 + eager-tracing same speed as framework=tf; Add more test coverage for tf2+tracing. (#19981) | 3 年之前 |
offline | dc51af798c [RLlib] Minor fix on json encoding during worker sampling (#20134) | 2 年之前 |
policy | 70fe25055a [RLlib] Issue: Get single step input dict incorrect. (#20217) | 2 年之前 |
tests | 246787cdd9 Revert "[RLlib] POC: `PGTrainer` class that works by sub-classing, not `trainer_template.py`. (#20055)" (#20284) | 2 年之前 |
tuned_examples | f3397b6f48 [RLlib] Minor fixes/cleanups; chop_into_sequences now handles nested data. (#19408) | 3 年之前 |
utils | 246787cdd9 Revert "[RLlib] POC: `PGTrainer` class that works by sub-classing, not `trainer_template.py`. (#20055)" (#20284) | 2 年之前 |
BUILD | ebd56b57db [RLlib; documentation] "RLlib in 60sec" overhaul. (#20215) | 2 年之前 |
README.md | 9b8218aabd [docs] Move all /latest links to /master (#11897) | 4 年之前 |
__init__.py | d001af3e59 [RLlib] Allow `rllib rollout` to run distributed via evaluation workers. (#13718) | 3 年之前 |
asv.conf.json | 5d7afe8092 [rllib] Try moving RLlib to top level dir (#5324) | 5 年之前 |
evaluate.py | e6aae61487 [RLlib; testing] Fix bug in stress tests not handling >1 trials per experiment (due to grid-search in IMPALA stress tests). (#18705) | 3 年之前 |
rollout.py | c5d20849ae [RLlib] Rename `rllib rollout` into `rllib evaluate` (backward compatible) to match Trainer API. (#18467) | 3 年之前 |
scripts.py | c5d20849ae [RLlib] Rename `rllib rollout` into `rllib evaluate` (backward compatible) to match Trainer API. (#18467) | 3 年之前 |
train.py | 38c456b6f4 [RLlib; Tune] Fix rllib/train.py script after tune.Experiment c'tor change. (#20283) | 2 年之前 |
RLlib is an open-source library for reinforcement learning that offers both high scalability and a unified API for a variety of applications.
For an overview of RLlib, see the documentation.
If you've found RLlib useful for your research, you can cite the paper as follows:
@inproceedings{liang2018rllib,
Author = {Eric Liang and
Richard Liaw and
Robert Nishihara and
Philipp Moritz and
Roy Fox and
Ken Goldberg and
Joseph E. Gonzalez and
Michael I. Jordan and
Ion Stoica},
Title = {{RLlib}: Abstractions for Distributed Reinforcement Learning},
Booktitle = {International Conference on Machine Learning ({ICML})},
Year = {2018}
}
You can develop RLlib locally without needing to compile Ray by using the setup-dev.py script. This sets up links between the rllib
dir in your git repo and the one bundled with the ray
package. When using this script, make sure that your git branch is in sync with the installed Ray binaries (i.e., you are up-to-date on master and have the latest wheel installed.)