Advantages and Limitations of using Successor Features for Transfer in Reinforcement Learning
Artificial Intelligence
2017-08-02 v1 Machine Learning
Machine Learning
Abstract
One question central to Reinforcement Learning is how to learn a feature representation that supports algorithm scaling and re-use of learned information from different tasks. Successor Features approach this problem by learning a feature representation that satisfies a temporal constraint. We present an implementation of an approach that decouples the feature representation from the reward function, making it suitable for transferring knowledge between domains. We then assess the advantages and limitations of using Successor Features for transfer.
Keywords
Cite
@article{arxiv.1708.00102,
title = {Advantages and Limitations of using Successor Features for Transfer in Reinforcement Learning},
author = {Lucas Lehnert and Stefanie Tellex and Michael L. Littman},
journal= {arXiv preprint arXiv:1708.00102},
year = {2017}
}