Market-based reinforcement learning in partially observable worlds
Date
2001
Authors
Kwee, Ivo
Hutter, Marcus
Schmidhuber, Jürgen
Journal Title
Journal ISSN
Volume Title
Publisher
Springer Verlag
Abstract
Unlike 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.
Description
Keywords
Hayek system, reinforcement learning, partial observable environment
Citation
Collections
Source
Artificial Neural Networks - ICANN 2001 Proceedings
Type
Conference paper
Book Title
Artificial Neural Networks - ICANN 2001: International Conference Vienna, Austria, August 21–25, 2001 Proceedings
Entity type
Access Statement
Open Access