Skip to Main content Skip to Navigation
Conference papers

Bayesian Multi-Task Reinforcement Learning

Alessandro Lazaric 1, * Mohammad Ghavamzadeh 1
* Corresponding author
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
Abstract : We consider the problem of multi-task reinforcement learning where the learner is provided with a set of tasks, for which only a small number of samples can be generated for 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 classes of tasks with similar structure 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 a common prior. We adopt the Gaussian process temporal-difference value function model 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.
Document type :
Conference papers
Complete list of metadata

Cited literature [17 references]  Display  Hide  Download
Contributor : Mohammad Ghavamzadeh Connect in order to contact the contributor
Submitted on : Wednesday, April 21, 2010 - 2:43:12 PM
Last modification on : Saturday, December 18, 2021 - 3:04:08 AM
Long-term archiving on: : Tuesday, September 28, 2010 - 1:08:32 PM


Files produced by the author(s)


  • HAL Id : inria-00475214, version 1



Alessandro Lazaric, Mohammad Ghavamzadeh. Bayesian Multi-Task Reinforcement Learning. ICML - 27th International Conference on Machine Learning, Jun 2010, Haifa, Israel. pp.599-606. ⟨inria-00475214⟩



Les métriques sont temporairement indisponibles