代码
注册 登录
简体中文
简体中文 English
openoker
/
ray
1
0
收藏 0
文件 工单管理 0 Wiki
分支: data-dashboard
分支列表 标签列表
Avnish Narayan 684e28b380 [RLlib] RLlib deprecation Notices Part 1 (algorithm/, evaluation/, execution/, models/jax/) (#36826) 1 年之前
..
tests 8e680c483c [RLlib] gymnasium support (new `Env.reset()/step()/seed()/render()` APIs). (#28369) 1 年之前
README.md 68a9a33386 [RLlib] Retry agents -> algorithms. with proper doc changes this time. (#24797) 2 年之前
__init__.py 8a9a176a24 [RLlib] Remove all default config objects and rllib/agents (#33242) 1 年之前
mbmpo.py 684e28b380 [RLlib] RLlib deprecation Notices Part 1 (algorithm/, evaluation/, execution/, models/jax/) (#36826) 1 年之前
mbmpo_torch_policy.py 827ab91741 [RLlib] Replace remaining mentions of "trainer" by "algorithm". (#36557) 1 年之前
model_ensemble.py 8e680c483c [RLlib] gymnasium support (new `Env.reset()/step()/seed()/render()` APIs). (#28369) 1 年之前
utils.py 7f431d7053 Bump black (and therefore click) versions (#29574) 2 年之前

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