Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

awesome-metarl

A curated list of awesome Meta Reinforcement Learning
https://github.com/metarl/awesome-metarl

Last synced: 3 days ago
JSON representation

Datasets
- Meta Lifelong Reinforcement Learning
  - Gym (Mojocu/Atari/...)
Papers
- Model-Free Meta Reinforcement Learning
  - [arXiv - RL)
  - [arXiv
  - [arXiv
  - [arXiv - based meta-RL)
  - [arXiv - based meta-RL)
  - [arXiv - based meta-RL, exploration with latent variables)
  - [arXiv - policy meta-RL with posterior sampling for exploration)
  - [arXiv
  - [arXiv
  - [arXiv
  - [arXiv
  - [arXiv - maml) Algorithm: E-MAML & E-RL2. (treat the adaptation step as part of the unknown dynamics of environment)
  - [arXiv
  - [arXiv
  - [arXiv - learning-rl)
  - [arXiv
  - [arXiv
  - [arXiv
  - [arXiv
  - [arXiv
  - [arXiv
  - [arXiv - research/google-research/tree/master/norml) Algorithm: NoRML. (MAML + environment dynamics)
- Model-Based Meta Reinforcement Learning
  - [arXiv
  - [arXiv
- Meta Imitation Learning
  - [arXiv
  - [arXiv - research/tensor2robot/tree/master/research/vrgripper) (demonstrateion + trial-and-error)
- Unsupervised Meta Reinforcement Learning
  - [arXiv
  - [arXiv - Fit. (maximize entropy)
- Meta Lifelong Reinforcement Learning
  - [arXiv
  - [arXiv
Blogs
- Meta Lifelong Reinforcement Learning
  - Meta Reinforcement Learning
  - Meta Reinforcement Learning

Programming Languages