Learning with whom to communicate using relational reinforcement learning

Authors:
Marc Ponsen;Tom Croonenborghs;Karl Tuyls;Jan Ramon;Kurt Driessens
Affiliations:
University of Maastricht, The Netherlands;KH Kempen, Belgium;Eindhoven University of Technology, The Netherlands;K.U. Leuven, Belgium;K.U. Leuven, Belgium
Venue:
Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems - Volume 2
Year:
2009

Citing 0
Cited 2

Abstraction and generalization in reinforcement learning: a summary and framework

ALA'09 Proceedings of the Second international conference on Adaptive and Learning Agents
Interactive relational reinforcement learning of concept semantics

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

Relational reinforcement learning (RRL) has emerged in the machine learning community as a new promising subfield of reinforcement learning (RL) (e.g. [1]). It upgrades RL techniques by using relational representations for states, actions and learned value-functions or policies to allow more natural representations and abstractions of complex tasks. This leads to a serious state space reduction, allowing to better generalize and infer new knowledge.