Market-Based Reinforcement Learning in Partially Observable Worlds

Simple item page
dc.creatorKwee, Ivo
dc.creatorHutter, Marcus
dc.creatorSchmidhuber, Juergen
dc.date2001-05-15
dc.date.accessioned2026-07-07T03:17:09Z
dc.date.available2026-07-07T03:17:09Z
dc.descriptionUnlike traditional reinforcement learning (RL), market-based RL is in principle applicable to worlds described by partially observable Markov Decision Processes (POMDPs), where an agent needs to learn short-term memories of relevant previous events in order to execute optimal actions. Most previous work, however, has focused on reactive settings (MDPs) instead of POMDPs. Here we reimplement a recent approach to market-based RL and for the first time evaluate it in a toy POMDP setting.
dc.description8 LaTeX pages, 2 postscript figures
dc.identifierhttps://arxiv.org/abs/cs/0105025
dc.identifierhttp://arxiv.org/abs/cs/0105025
dc.identifierLecture Notes in Computer Science (LNCS 2130), Proceeding of the International Conference on Artificial Neural Networks ICANN (2001) 865-873
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/30617
dc.subjectArtificial Intelligence
dc.subjectMachine Learning
dc.subjectMultiagent Systems
dc.subjectNeural and Evolutionary Computing
dc.subjectI.2
dc.titleMarket-Based Reinforcement Learning in Partially Observable Worlds
dc.typetext

Files

Collections

arXiv