Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning

Ronan Fruit
  • Function : Author
Matteo Pirotta
  • Function : Author
  • PersonId : 1023840
Alessandro Lazaric


We introduce SCAL, an algorithm designed to perform efficient exploration-exploitation in any unknown weakly-communicating Markov decision process (MDP) for which an upper bound $c$ on the span of the optimal bias function is known. For an MDP with $S$ states, $A$ actions and $\Gamma \leq S$ possible next states, we prove a regret bound of $\widetilde{O}(c\sqrt{\Gamma SAT})$, which significantly improves over existing algorithms (e.g., UCRL and PSRL), whose regret scales linearly with the MDP diameter $D$. In fact, the optimal bias span is finite and often much smaller than $D$ (e.g., $D=\infty$ in non-communicating MDPs). A similar result was originally derived by Bartlett and Tewari (2009) for REGAL.C, for which no tractable algorithm is available. In this paper, we relax the optimization problem at the core of REGAL.C, we carefully analyze its properties, and we provide the first computationally efficient algorithm to solve it. Finally, we report numerical simulations supporting our theoretical findings and showing how SCAL significantly outperforms UCRL in MDPs with large diameter and small span.
Fichier principal
Vignette du fichier
fruit18a-supp.pdf (805.56 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01941206 , version 1 (30-11-2018)


  • HAL Id : hal-01941206 , version 1


Ronan Fruit, Matteo Pirotta, Alessandro Lazaric, Ronald Ortner. Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning. ICML 2018 - The 35th International Conference on Machine Learning, Jul 2018, Stockholm, Sweden. pp.1578-1586. ⟨hal-01941206⟩
64 View
35 Download


Gmail Facebook Twitter LinkedIn More