Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning - Archive ouverte HAL Access content directly
Conference Papers Year : 2013

Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning

(1) , (2) , (1) , (3)
1
2
3

Abstract

We consider an agent interacting with an environment in a single stream of actions, observations, and rewards, with no reset. This process is not assumed to be a Markov Decision Process (MDP). Rather, the agent has several representations (mapping histories of past interactions to a discrete state space) of the environment with unknown dynamics, only some of which result in an MDP. The goal is to minimize the average regret criterion against an agent who knows an MDP representation giving the highest optimal reward, and acts optimally in it. Recent regret bounds for this setting are of order $O(T^{2/3})$ with an additive term constant yet exponential in some characteristics of the optimal MDP. We propose an algorithm whose regret after $T$ time steps is $O(\sqrt{T})$, with all constants reasonably small. This is optimal in $T$ since $O(\sqrt{T})$ is the optimal regret in the setting of learning in a (single discrete) MDP.
Fichier principal
Vignette du fichier
icml1_iblb_cr-corrected.pdf (179.28 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00778586 , version 1 (20-03-2013)

Identifiers

  • HAL Id : hal-00778586 , version 1

Cite

Odalric-Ambrym Maillard, Phuong Nguyen, Ronald Ortner, Daniil Ryabko. Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning. ICML - 30th International Conference on Machine Learning, 2013, Atlanta, USA, United States. pp.543-551. ⟨hal-00778586⟩
189 View
124 Download

Share

Gmail Facebook Twitter LinkedIn More