Universal Reinforcement Learning

Details Universal Reinforcement Learning Universal Reinforcement Learning

2007-07-20

arxiv.org/abs/0707.3087v3

Computer Science

Information Theory

Scientific paper

We consider an agent interacting with an unmodeled environment. At each time, the agent makes an observation, takes an action, and incurs a cost. Its actions can influence future observations and costs. The goal is to minimize the long-term average cost. We propose a novel algorithm, known as the active LZ algorithm, for optimal control based on ideas from the Lempel-Ziv scheme for universal data compression and prediction. We establish that, under the active LZ algorithm, if there exists an integer $K$ such that the future is conditionally independent of the past given a window of $K$ consecutive actions and observations, then the average cost converges to the optimum. Experimental results involving the game of Rock-Paper-Scissors illustrate merits of the algorithm.

Affiliated with

Also associated with

No associations

Rating

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

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-399043