Transferring evolved reservoir features in reinforcement learning tasks

Authors:
Kyriakos C. Chatzidimitriou;Ioannis Partalas;Pericles A. Mitkas;Ioannis Vlahavas
Affiliations:
Dept. of Electrical & Computer Engineering, Aristotle University of Thessaloniki, Greece,Informatics and Telematics Institute, Centre for Research and Technology, Hellas, Greece;Dept. of Informatics, Aristotle University of Thessaloniki, Greece;Dept. of Electrical & Computer Engineering, Aristotle University of Thessaloniki, Greece,Informatics and Telematics Institute, Centre for Research and Technology, Hellas, Greece;Dept. of Informatics, Aristotle University of Thessaloniki, Greece
Venue:
EWRL'11 Proceedings of the 9th European conference on Recent Advances in Reinforcement Learning
Year:
2011

Citing 15
Cited 1

Reinforcement learning with replacing eligibility traces

Machine Learning - Special issue on reinforcement learning
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Evolving neural networks through augmenting topologies

Evolutionary Computation
Transfer of Experience Between Reinforcement Learning Environments with Progressive Difficulty

Artificial Intelligence Review
Probabilistic policy reuse in a reinforcement learning agent

AAMAS '06 Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems
Evolutionary Function Approximation for Reinforcement Learning

The Journal of Machine Learning Research
Transfer via inter-task mappings in policy search reinforcement learning

Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems
Autonomous transfer for reinforcement learning

Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 1
Transferring Instances for Model-Based Reinforcement Learning

ECML PKDD '08 Proceedings of the European conference on Machine Learning and Knowledge Discovery in Databases - Part II
Learning and multiagent reasoning for autonomous agents

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Transfer Learning for Reinforcement Learning Domains: A Survey

The Journal of Machine Learning Research
RL-Glue: Language-Independent Software for Reinforcement-Learning Experiments

The Journal of Machine Learning Research
A NEAT Way for Evolving Echo State Networks

Proceedings of the 2010 conference on ECAI 2010: 19th European Conference on Artificial Intelligence
Skill acquisition via transfer learning and advice taking

ECML'06 Proceedings of the 17th European conference on Machine Learning
Reinforcement learning with echo state networks

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I

Transferring task models in Reinforcement Learning agents

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The major goal of transfer learning is to transfer knowledge acquired on a source task in order to facilitate learning on another, different, but usually related, target task. In this paper, we are using neuroevolution to evolve echo state networks on the source task and transfer the best performing reservoirs to be used as initial population on the target task. The idea is that any non-linear, temporal features, represented by the neurons of the reservoir and evolved on the source task, along with reservoir properties, will be a good starting point for a stochastic search on the target task. In a step towards full autonomy and by taking advantage of the random and fully connected nature of echo state networks, we examine a transfer method that renders any inter-task mappings of states and actions unnecessary. We tested our approach and that of inter-task mappings in two RL testbeds: the mountain car and the server job scheduling domains. Under various setups the results we obtained in both cases are promising.