Nonparametric Bayesian Policy Priors for Reinforcement Learning
Finale P Doshi-Velez ⋅ David Wingate ⋅ Nicholas Roy ⋅ Josh Tenenbaum
2010 Poster
Abstract
We consider reinforcement learning in partially observable domains where the agent can query an expert for demonstrations. Our nonparametric Bayesian approach combines model knowledge, inferred from expert information and independent exploration, with policy knowledge inferred from expert trajectories. We introduce priors that bias the agent towards models with both simple representations and simple policies, resulting in improved policy and model learning.
Chat is not available.
Successful Page Load