Some Considerations on Learning to Explore via Meta-Reinforcement Learning

Bradly Stadie, Ge Yang, Rein Houthooft, Xi Chen, Yan Duan, Yuhuai Wu, Pieter Abbeel, Ilya Sutskever

Abstract: We consider the problem of exploration in meta reinforcement learning. Two new meta reinforcement learning algorithms are suggested: E-MAML and ERL2. Results are presented on a novel environment we call 'Krazy World' and a set of maze environments. We show E-MAML and ERL2 deliver better performance on tasks where exploration is important.

TL;DR: Modifications to MAML and RL2 that should allow for better exploration.

Keywords: reinforcement learning, rl, exploration, meta learning, meta reinforcement learning, curiosity

Code: [ episodeyang/e-maml](https://github.com/episodeyang/e-maml) + [ 6 community implementations](https://paperswithcode.com/paper/?openreview=Skk3Jm96W)

Community Implementations: [ 7 code implementations](https://www.catalyzex.com/paper/arxiv:1803.01118/code)