Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence

Simple item page
dc.creatorRyabko, Daniil
dc.creatorHutter, Marcus
dc.date2006-03-28
dc.date.accessioned2026-07-07T07:05:56Z
dc.date.available2026-07-07T07:05:56Z
dc.descriptionWe address the problem of reinforcement learning in which observations may exhibit an arbitrary form of stochastic dependence on past observations and actions. The task for an agent is to attain the best possible asymptotic reward where the true generating environment is unknown but belongs to a known countable family of environments. We find some sufficient conditions on the class of environments under which an agent exists which attains the best asymptotic reward for any environment in the class. We analyze how tight these conditions are and how they relate to different probabilistic assumptions known in reinforcement learning and related fields, such as Markov Decision Processes and mixing conditions.
dc.description15 pages
dc.identifierhttps://arxiv.org/abs/cs/0603110
dc.identifierhttp://arxiv.org/abs/cs/0603110
dc.identifierProc. 17th International Conf. on Algorithmic Learning Theory (ALT 2006) pages 334-347
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/109843
dc.subjectMachine Learning
dc.subjectArtificial Intelligence
dc.titleAsymptotic Learnability of Reinforcement Problems with Arbitrary Dependence
dc.typetext

Files

Collections

arXiv