Preference elicitation and inverse reinforcement learning

Details Preference elicitation and inverse reinforcement learning Preference elicitation and inverse reinforcement learning

2011-04-29

arxiv.org/abs/1104.5687v2

Statistics

Machine Learning

13 pages, 4 figures; ECML 2011

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Preference elicitation and inverse reinforcement learning does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Preference elicitation and inverse reinforcement learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Preference elicitation and inverse reinforcement learning will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-18164