hiro/ray
1
0
Fork 0
mirror of https://github.com/vale981/ray synced 2025-03-05 18:11:42 -05:00
Code Issues Projects Releases Packages Wiki Activity Actions

SAC site changes (#6759)

Browse source
This commit is contained in:
Michael Luo 2020-01-09 18:13:42 -08:00 • committed by Eric Liang
parent f69081242e
commit e5dded917c
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
doc/source/rllib-algorithms.rst
View file

@ -278,12 +278,12 @@ RLlib's soft-actor critic implementation is ported from the `official SAC repo <
Tuned examples: `Pendulum-v0 <https://github.com/ray-project/ray/blob/master/rllib/tuned_examples/regression_tests/pendulum-sac.yaml>`__, `HalfCheetah-v3 <https://github.com/ray-project/ray/blob/master/rllib/tuned_examples/halfcheetah-sac.yaml>`__
**MuJoCo results @500k steps:** `more details <https://github.com/ray-project/rl-experiments>`__
**MuJoCo results @3M steps:** `more details <https://github.com/ray-project/rl-experiments>`__
============= ========== ===================
MuJoCo env RLlib SAC Haarnoja et al SAC
============= ========== ===================
HalfCheetah 8752 ~9000
HalfCheetah 13000 ~15000
============= ========== ===================
**SAC-specific configs** (see also `common configs <rllib-training.html#common-parameters>`__):