Multi-Task reinforcement learning: shaping and feature selection

Authors:
Matthijs Snel;Shimon Whiteson
Affiliations:
Intelligent Systems Lab Amsterdam (ISLA), University of Amsterdam, Amsterdam, Netherlands;Intelligent Systems Lab Amsterdam (ISLA), University of Amsterdam, Amsterdam, Netherlands
Venue:
EWRL'11 Proceedings of the 9th European conference on Recent Advances in Reinforcement Learning
Year:
2011

Citing 13
Cited 4

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Random Forests

Machine Learning
Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping

ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Autonomous shaping: knowledge transfer in reinforcement learning

ICML '06 Proceedings of the 23rd international conference on Machine learning
Multi-task reinforcement learning: a hierarchical Bayesian approach

Proceedings of the 24th international conference on Machine learning
An analysis of linear models, linear value-function approximation, and feature selection for reinforcement learning

Proceedings of the 25th international conference on Machine learning
Co-evolution of Shaping Rewards and Meta-Parameters in Reinforcement Learning

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Transfer via soft homomorphisms

Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems - Volume 2
Potential-based shaping in model-based reinforcement learning

AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 2
State abstraction discovery from irrelevant state variables

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Transfer Learning for Reinforcement Learning Domains: A Survey

The Journal of Machine Learning Research
Multi-task evolutionary shaping without pre-specified representations

Proceedings of the 12th annual conference on Genetic and evolutionary computation
Feature selection for reinforcement learning: evaluating implicit state-reward dependency via conditional mutual information

ECML PKDD'10 Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part I

Robust bayesian reinforcement learning through tight lower bounds

EWRL'11 Proceedings of the 9th European conference on Recent Advances in Reinforcement Learning
Machine learning for interactive systems and robots: a brief introduction

Proceedings of the 2nd Workshop on Machine Learning for Interactive Systems: Bridging the Gap Between Perception, Action and Communication
Construction of approximation spaces for reinforcement learning

The Journal of Machine Learning Research
Learning potential functions and their representations for multi-task reinforcement learning

Autonomous Agents and Multi-Agent Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced source tasks to speed up learning on a new target task. Earlier work has not clearly motivated choices for the shaping function. This paper discusses and empirically compares several alternatives, and demonstrates that the most intuive one may not always be the best option. In addition, we extend previous work on identifying good representations for the value and shaping functions, and show that selecting the right representation results in improved generalization over tasks.