Some Considerations on Learning to Explore via Meta-Reinforcement Learning

• Abstract
• Abstract (translated by Google)
• URL
• PDF

Abstract

We consider the problem of exploration in meta reinforcement learning. Two new meta reinforcement learning algorithms are suggested: E-MAML and E-$\text{RL}^2$. Results are presented on a novel environment we call `Krazy World’ and a set of maze environments. We show E-MAML and E-$\text{RL}^2$ deliver better performance on tasks where exploration is important.

Abstract (translated by Google)

URL

http://arxiv.org/abs/1803.01118

PDF

http://arxiv.org/pdf/1803.01118