wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-08-14 12:40:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

MBMPO Cartpole (#11832)

Browse Source 
* MBMPO Cartpole Done

* Added doc
This commit is contained in:
Michael Luo
2020-11-12 10:30:41 -08:00
committed by GitHub
parent 9254de0b02
commit 6e6c680f14
6 changed files with 68 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/source/rllib-algorithms.rst
+6 -1
View File
@@ -471,7 +471,12 @@ RLlib's MBMPO implementation is a Dyna-styled model-based RL method that learns
Additional statistics are logged in MBMPO. Each MBMPO iteration corresponds to multiple MAML iterations, and ``MAMLIter$i$_DynaTrajInner_$j$_episode_reward_mean`` measures the agent's returns across the dynamics models at iteration ``i`` of MAML and step ``j`` of inner adaptation. Examples can be seen `here <https://github.com/ray-project/rl-experiments/tree/master/mbmpo>`__.
Tuned examples: `HalfCheetah <https://github.com/ray-project/ray/blob/master/rllib/tuned_examples/mbmpo/halfcheetah-mbmpo.yaml>`__, `Hopper <https://github.com/ray-project/ray/blob/master/rllib/tuned_examples/mbmpo/hopper-mbmpo.yaml>`__
Tuned examples (continuous actions):
`Pendulum-v0 <https://github.com/ray-project/ray/blob/master/rllib/tuned_examples/mbmpo/pendulum-mbmpo.yaml>`__,
`HalfCheetah <https://github.com/ray-project/ray/blob/master/rllib/tuned_examples/mbmpo/halfcheetah-mbmpo.yaml>`__,
`Hopper <https://github.com/ray-project/ray/blob/master/rllib/tuned_examples/mbmpo/hopper-mbmpo.yaml>`__,
Tuned examples (discrete actions):
`CartPole-v0 <https://github.com/ray-project/ray/blob/master/rllib/tuned_examples/mbmpo/cartpole-mbmpo.yaml>`__
**MuJoCo results @100K steps:** `more details <https://github.com/ray-project/rl-experiments>`__