On-line Reinforcement Learning Using Incremental Kernel-Based Stochastic Factorization

Kernel-based stochastic factorization (KBSF) is an algorithm for solving reinforcement learningtasks with continuous state spaces which builds a Markov decision process (MDP) based on a set of sample transitions. What sets KBSF apart from other kernel-based approaches is the fact that the size of its MDP is independent ofthe number of transitions, which makes it possible to control the tradeoff between the quality of the resulting approximation and the associated computational cost.However, KBSF's memory usage grows linearly with the number of transitions, precluding its application in scenarios where a large amount of data must be processed. In this paper we show that it is possible to construct KBSF's MDP in a fully incremental way, thus freeing the space complexity of this algorithm fromits dependence on the number of sample transitions. The incremental version of KBSF is able to process an arbitrary amount of data, which results in a model-based reinforcement learning algorithm that can be used to solve continuous MDPsin both off-line and online regimes. We present theoretical results showing that KBSF can approximate the value function that would be computed by conventional kernel-based learning with arbitrary precision. We empirically demonstrate the effectiveness of the proposed algorithm in the challenging threepole balancingtask, in which the ability to process a large number of transitions is crucial for success.