Skip to Main content Skip to Navigation
Conference papers

Near-Optimal BRL using Optimistic Local Transitions

Mauricio Araya-López 1 Vincent Thomas 1 Olivier Buffet 1 
1 MAIA - Autonomous intelligent machine
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
Abstract : Model-based Bayesian Reinforcement Learning (BRL) allows a sound formalization of the problem of acting optimally while facing an unknown environment, i.e., avoiding the exploration-exploitation dilemma. However, algorithms explicitly addressing BRL suffer from such a combinatorial explosion that a large body of work relies on heuristic algorithms. This paper introduces bolt, a simple and (almost) deterministic heuristic algorithm for BRL which is optimistic about the transition function. We analyze bolt's sample complexity, and show that under certain parameters, the algorithm is near-optimal in the Bayesian sense with high probability. Then, experimental results highlight the key differences of this method compared to previous work.
Document type :
Conference papers
Complete list of metadata

Cited literature [15 references]  Display  Hide  Download
Contributor : Olivier Buffet Connect in order to contact the contributor
Submitted on : Tuesday, November 20, 2012 - 6:44:42 PM
Last modification on : Saturday, June 25, 2022 - 7:46:31 PM
Long-term archiving on: : Thursday, February 21, 2013 - 12:32:01 PM


Files produced by the author(s)


  • HAL Id : hal-00755270, version 1



Mauricio Araya-López, Vincent Thomas, Olivier Buffet. Near-Optimal BRL using Optimistic Local Transitions. International Conference on Machine Learning - ICML 2012, Jun 2012, Edimburgh, United Kingdom. ⟨hal-00755270⟩



Record views


Files downloads