Work

A Monte-Carlo AIXI Approximation

Year: 2011
Type: article
Abstract: This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. Our 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 new Monte-Carlo Tree Search algorithm along with an agent-specific extension to the Context Tree Weighting algorithm. Empirically, we present a set of encouraging results on a variety of stochastic and partially observable domains. We conclude by proposing a number of directions for future research.
Authors: J. Veness, K.S. Ng, M. Hutter, W. Uther, D. Silver
Language: English
Open Access status: diamond
OpenAlex ID: W2124016254
FWCI: 17.53
Cites: 118
Cited by: 207
Related to: 9