hiro/ray
1
0
Fork 0
mirror of https://github.com/vale981/ray synced 2025-03-06 10:31:39 -05:00
Code Issues Projects Releases Packages Wiki Activity Actions
ray/rllib/algorithms/mbmpo
History
Jun Gong d5a6d46049
[RLlib] Migrate MAML, MB-MPO, MARWIL, and BC to use Policy sub-classing implementation. (#24914)
2022-05-20 14:10:59 +02:00
..
tests [RLlib] Retry agents -> algorithms. with proper doc changes this time. (#24797) 2022-05-16 09:45:32 +02:00
__init__.py [RLlib] Retry agents -> algorithms. with proper doc changes this time. (#24797) 2022-05-16 09:45:32 +02:00
mbmpo.py [RLlib] Migrate MAML, MB-MPO, MARWIL, and BC to use Policy sub-classing implementation. (#24914) 2022-05-20 14:10:59 +02:00
mbmpo_torch_policy.py [RLlib] Migrate MAML, MB-MPO, MARWIL, and BC to use Policy sub-classing implementation. (#24914) 2022-05-20 14:10:59 +02:00
model_ensemble.py [RLlib] Retry agents -> algorithms. with proper doc changes this time. (#24797) 2022-05-16 09:45:32 +02:00
README.md [RLlib] Retry agents -> algorithms. with proper doc changes this time. (#24797) 2022-05-16 09:45:32 +02:00
utils.py [RLlib] Retry agents -> algorithms. with proper doc changes this time. (#24797) 2022-05-16 09:45:32 +02:00

README.md

Model-based Meta-Policy Optimization (MB-MPO)

Code in this package is adapted from https://github.com/jonasrothfuss/model_ensemble_meta_learning.

Overview

MBMPO is an on-policy model-based algorithm. On a high level, MBMPO is model-based MAML. On top of MAML, MBMPO learns an ensemble of dynamics models. MBMPO trains the dynamics models with real-life data and the actor/critic networks with fake data generated by the dynamics models. The actor and critic are updated via the MAML algorithm. For the distributed execution plan, MBMPO alternates between training the dynanmics model and training the actor and critic network.

More details can be found here.

Documentation & Implementation:

MBMPO.

Detailed Documentation

Implementation