On the Possibility of Learning in Reactive Environments with Arbitrary
Dependence

On the Possibility of Learning in Reactive Environments with Arbitrary Dependence

31 October 2008

Marcus Hutter

ArXiv (abs)PDF HTML

Papers citing "On the Possibility of Learning in Reactive Environments with Arbitrary Dependence"

14 / 14 papers shown

Title
On Reward Structures of Markov Decision Processes Falcon Z. Dai 13 1 0 28 Aug 2023
Universal time-series forecasting with mixture predictors D. Ryabko AI4TS 88 0 0 01 Oct 2020
Learning and Planning for Time-Varying MDPs Using Maximum Likelihood Estimation Melkior Ornik Ufuk Topcu OOD 26 15 0 29 Nov 2019
The Sample-Complexity of General Reinforcement Learning Tor Lattimore Marcus Hutter P. Sunehag VLM 113 67 0 22 Aug 2013
Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning Odalric-Ambrym Maillard P. Nguyen R. Ortner D. Ryabko 110 30 0 11 Feb 2013
Selecting the State-Representation in Reinforcement Learning Odalric-Ambrym Maillard Rémi Munos D. Ryabko 90 40 0 11 Feb 2013
Deterministic MDPs with Adversarial Rewards and Bandit Feedback R. Arora O. Dekel Ambuj Tewari 118 32 0 16 Oct 2012
Optimistic Agents are Asymptotically Optimal P. Sunehag Marcus Hutter 96 14 0 29 Sep 2012
Regret Bounds for Restless Markov Bandits R. Ortner D. Ryabko P. Auer Rémi Munos 111 117 0 12 Sep 2012
Online Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret R. Arora O. Dekel Ambuj Tewari OffRL 119 196 0 27 Jun 2012
Asymptotically Optimal Agents Tor Lattimore Marcus Hutter AI4CE 125 36 0 27 Jul 2011
On Finding Predictors for Arbitrary Families of Processes D. Ryabko 64 13 0 24 Dec 2009
Open Problems in Universal Induction & Intelligence Marcus Hutter AI4CE 172 32 0 04 Jul 2009
A Minimum Relative Entropy Principle for Learning and Acting Pedro A. Ortega Daniel A. Braun 142 125 0 20 Oct 2008