Skip to Main content Skip to Navigation
Conference papers

Exploration–Exploitation in MDPs with Options

Ronan Fruit 1, 2 Alessandro Lazaric 1, 2
1 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : While a large body of empirical results show that temporally-extended actions and options may significantly affect the learning performance of an agent, the theoretical understanding of how and when options can be beneficial in online reinforcement learning is relatively limited. In this paper, we derive an upper and lower bound on the regret of a variant of UCRL using options. While we first analyze the algorithm in the general case of semi-Markov decision processes (SMDPs), we show how these results can be translated to the specific case of MDPs with options and we illustrate simple scenarios in which the regret of learning with options can be provably much smaller than the regret suffered when learning with primitive actions.
Document type :
Conference papers
Complete list of metadata
Contributor : Alessandro Lazaric Connect in order to contact the contributor
Submitted on : Friday, March 24, 2017 - 3:55:40 PM
Last modification on : Friday, January 21, 2022 - 3:13:18 AM
Long-term archiving on: : Sunday, June 25, 2017 - 1:34:33 PM


Files produced by the author(s)


  • HAL Id : hal-01493567, version 2



Ronan Fruit, Alessandro Lazaric. Exploration–Exploitation in MDPs with Options. AISTATS 2017 - 20th International Conference on Artificial Intelligence and Statistics, Apr 2017, Fort Lauderdale, United States. ⟨hal-01493567v2⟩



Les métriques sont temporairement indisponibles