| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning
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.
Cited literature [14 references]
https://hal.inria.fr/hal-00778586
Contributor : Daniil Ryabko Connect in order to contact the contributor
Submitted on : Wednesday, March 20, 2013 - 10:52:14 AM
Last modification on : Thursday, January 20, 2022 - 4:12:35 PM
Long-term archiving on: : Friday, June 21, 2013 - 4:12:20 AM
Contributor : Daniil Ryabko Connect in order to contact the contributor
Submitted on : Wednesday, March 20, 2013 - 10:52:14 AM
Last modification on : Thursday, January 20, 2022 - 4:12:35 PM
Long-term archiving on: : Friday, June 21, 2013 - 4:12:20 AM
File
icml1_iblb_cr-corrected.pdf
Files produced by the author(s)