Market-Based Reinforcement Learning in Partially Observable Worlds

Authors:
Ivo Kwee;Marcus Hutter;Jürgen Schmidhuber
Affiliations:
-;-;-
Venue:
ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Year:
2001

Citing 11
Cited 0

Reinforcement learning in Markovian and non-Markovian environments

NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
Technical Note: \cal Q-Learning

Machine Learning
Adding temporary memory to ZCS

Adaptive Behavior
Continual learning in reinforcement environments

Continual learning in reinforcement environments
Shifting Inductive Bias with Success-Story Algorithm, AdaptiveLevin Search, and Incremental Self-Improvement

Machine Learning - Special issue on inductive transfer
HQ-learning

Adaptive Behavior
Toward a Model of Intelligence as an Economy of Agents

Machine Learning
Learning to Predict by the Methods of Temporal Differences

Machine Learning
Properties of the Bucket Brigade

Proceedings of the 1st International Conference on Genetic Algorithms
Planning and Acting in Partially Observable Stochastic Domains

Planning and Acting in Partially Observable Stochastic Domains
Zcs: A zeroth level classifier system

Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Unlike traditional reinforcement learning (RL), marketbased 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.