Some considerations on learning to explore via meta-reinforcement learning

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

Research output: Contribution to journalConference articlepeer-review

22 Scopus citations

Abstract

We interpret meta-reinforcement learning as the problem of learning how to quickly find a good sampling distribution in a new environment. This interpretation leads to the development of two new meta-reinforcement learning algorithms: E-MAML and E-RL2. Results are presented on a new environment we call 'Krazy World': a difficult high-dimensional gridworld which is designed to highlight the importance of correctly differentiating through sampling distributions in meta-reinforcement learning. Further results are presented on a set of maze environments. We show E-MAML and E-RL2 deliver better performance than baseline algorithms on both tasks.

Original languageEnglish (US)
Pages (from-to)9280-9290
Number of pages11
JournalAdvances in Neural Information Processing Systems
Volume2018-December
StatePublished - 2018
Event32nd Conference on Neural Information Processing Systems, NeurIPS 2018 - Montreal, Canada
Duration: Dec 2 2018Dec 8 2018

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'Some considerations on learning to explore via meta-reinforcement learning'. Together they form a unique fingerprint.

Cite this