Optimal Regret Bounds for Selecting the State Representation in
Reinforcement Learning

v1v2 (latest)

Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning

11 February 2013

Odalric-Ambrym Maillard

ArXiv (abs)PDF HTML

Papers citing "Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning"

11 / 11 papers shown

Title
An Analysis of Model-Based Reinforcement Learning From Abstracted Observations Rolf A. N. Starre Marco Loog E. Congeduti F. Oliehoek OffRL 59 1 0 30 Aug 2022
Regret Balancing for Bandit and RL Model Selection Yasin Abbasi-Yadkori Aldo Pacchiano My Phan 87 26 0 09 Jun 2020
Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes Ronan Fruit Matteo Pirotta A. Lazaric 82 62 0 06 Jul 2018
A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity Pablo Hernandez-Leal Michael Kaisers T. Baarslag Enrique Munoz de Cote 88 275 0 28 Jul 2017
Extreme State Aggregation Beyond MDPs Marcus Hutter 168 23 0 12 Jul 2014
Selecting Near-Optimal Approximate State Representations in Reinforcement Learning R. Ortner Odalric-Ambrym Maillard D. Ryabko 238 27 0 12 May 2014
The Sample-Complexity of General Reinforcement Learning Tor Lattimore Marcus Hutter P. Sunehag VLM 113 67 0 22 Aug 2013
Regret Bounds for Reinforcement Learning with Policy Advice M. G. Azar A. Lazaric Emma Brunskill 127 36 0 05 May 2013
Unsupervised model-free representation learning D. Ryabko CML AI4TS 33 2 0 17 Apr 2013
Online Regret Bounds for Undiscounted Continuous Reinforcement Learning R. Ortner D. Ryabko OffRL 120 85 0 11 Feb 2013
Regret Bounds for Restless Markov Bandits R. Ortner D. Ryabko P. Auer Rémi Munos 125 117 0 12 Sep 2012