Reinforcement Learning via AIXI Approximation

Details Reinforcement Learning via AIXI Approximation Reinforcement Learning via AIXI Approximation

2010-07-13

arxiv.org/abs/1007.2049v1

Proc. 24th AAAI Conference on Artificial Intelligence (AAAI 2010) pages 605-611

Computer Science

Learning

8 LaTeX pages, 1 figure

Scientific paper

This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. This approach is based on a direct approximation of AIXI, a Bayesian optimality notion for general reinforcement learning agents. Previously, it has been unclear whether the theory of AIXI could motivate the design of practical algorithms. We answer this hitherto open question in the affirmative, by providing the first computationally feasible approximation to the AIXI agent. To develop our approximation, we introduce a Monte Carlo Tree Search algorithm along with an agent-specific extension of the Context Tree Weighting algorithm. Empirically, we present a set of encouraging results on a number of stochastic, unknown, and partially observable domains.

Affiliated with

Also associated with

No associations

Rating

Reinforcement Learning via AIXI Approximation 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 Reinforcement Learning via AIXI Approximation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Reinforcement Learning via AIXI Approximation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-350510