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

Feb 15, 2018 (modified: Feb 15, 2018) ICLR 2018 Conference Blind Submission readers: everyone Show Bibtex
  • 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