Preference elicitation and inverse reinforcement learning

9 years 2 months ago
Preference elicitation and inverse reinforcement learning
We state the problem of inverse reinforcement learning in terms of preference elicitation, resulting in a principled (Bayesian) statistical formulation. This generalises previous work on Bayesian inverse reinforcement learning and allows us to obtain a posterior distribution on the agent's preferences, policy and optionally, the obtained reward sequence, from observations. We examine the relation of the resulting approach to other statistical methods for inverse reinforcement learning via analysis and experimental results. We show that preferences can be determined accurately, even if the observed agent's policy is sub-optimal with respect to its own preferences. In that case, significantly improved policies with respect to the agent's preferences are obtained, compared to both other methods and to the performance of the demonstrated policy.
Constantin Rothkopf, Christos Dimitrakakis
Added 02 Oct 2011
Updated 02 Oct 2011
Type Conference
Year 2011
Where ECML
Authors Constantin Rothkopf, Christos Dimitrakakis
Comments (0)