Bayesian Multi-Task Reinforcement Learning
Year: 2010
Type: article
Abstract: We consider the problem of multi-task reinforcement learning where the learner is provided with a set of tasks, for which only a smallnumber ofsamplescanbe generatedfor any given policy. As the number of samples may not be enough to learn an accurate evaluation of the policy, it would be necessary to identify classesoftaskswith similarstructure and to learn them jointly. We consider the case where the tasks share structure in their value functions, and model this by assuming that the value functions are all sampled from acommonprior. Weadopt the Gaussianprocesstemporal-differencevaluefunctionmodel and use a hierarchical Bayesian approach to model the distribution over the value functions. We study two cases, where all the value functions belong to the same class and where they belong to an undefined number of classes. For each case, we present a hierarchical Bayesian model, and derive inference algorithms for (i) joint learning of the value functions, and (ii) efficient transfer of the information gained in (i) to assist learning the value function of a newly observed task. 1.
Authors: Alessandro Lazaric, Mohammad Ghavamzadeh
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2134197408