Sciweavers

AAAI
2010

Reinforcement Learning via AIXI Approximation

14 years 27 days ago
Reinforcement Learning via AIXI Approximation
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 agentspecific 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.
Joel Veness, Kee Siong Ng, Marcus Hutter, David Si
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2010
Where AAAI
Authors Joel Veness, Kee Siong Ng, Marcus Hutter, David Silver
Comments (0)