PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Logarithmic Online Regret Bound for Undiscounted Reinforcement Learning
Peter Auer and Ronald Ortner
In: NIPS 2006, 4-7 Dec 2006, Vancouver, Canada.


We present a learning algorithm for undiscounted reinforcement learning. Our interest lies in bounds for the algorithm's online performance after some finite number of steps. In the spirit of similar methods already successfully applied for the exploration-exploitation tradeoff in multi-armed bandit problems, we use upper confidence bounds to show that our UCRL algorithm achieves logarithmic online regret in the number of steps taken with respect to an optimal policy.

EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:2541
Deposited By:Ronald Ortner
Deposited On:22 November 2006