Avnish Narayan 684e28b380 [RLlib] RLlib deprecation Notices Part 1 (algorithm/, evaluation/, execution/, models/jax/) (#36826) | 1 year ago | |
---|---|---|
.. | ||
tests | 8e680c483c [RLlib] gymnasium support (new `Env.reset()/step()/seed()/render()` APIs). (#28369) | 1 year ago |
README.md | 68a9a33386 [RLlib] Retry agents -> algorithms. with proper doc changes this time. (#24797) | 2 years ago |
__init__.py | 8a9a176a24 [RLlib] Remove all default config objects and rllib/agents (#33242) | 1 year ago |
mbmpo.py | 684e28b380 [RLlib] RLlib deprecation Notices Part 1 (algorithm/, evaluation/, execution/, models/jax/) (#36826) | 1 year ago |
mbmpo_torch_policy.py | 827ab91741 [RLlib] Replace remaining mentions of "trainer" by "algorithm". (#36557) | 1 year ago |
model_ensemble.py | 8e680c483c [RLlib] gymnasium support (new `Env.reset()/step()/seed()/render()` APIs). (#28369) | 1 year ago |
utils.py | 7f431d7053 Bump black (and therefore click) versions (#29574) | 2 years ago |
Code in this package is adapted from https://github.com/jonasrothfuss/model_ensemble_meta_learning.
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.
MBMPO.