Selective Experience Replay for Lifelong Learning

Authors

  • David Isele University of Pennsylvania, Honda Research Institute
  • Akansel Cosgun Honda Research Institute

DOI:

https://doi.org/10.1609/aaai.v32i1.11595

Keywords:

Lifelong Machine Learning, Transfer Learning, Multi-task Learning, Experience Replay

Abstract

Deep reinforcement learning has emerged as a powerful tool for a variety of learning tasks, however deep nets typically exhibit forgetting when learning multiple tasks in sequence. To mitigate forgetting, we propose an experience replay process that augments the standard FIFO buffer and selectively stores experiences in a long-term memory. We explore four strategies for selecting which experiences will be stored: favoring surprise, favoring reward, matching the global training distribution, and maximizing coverage of the state space. We show that distribution matching successfully prevents catastrophic forgetting, and is consistently the best approach on all domains tested. While distribution matching has better and more consistent performance, we identify one case in which coverage maximization is beneficial---when tasks that receive less trained are more important. Overall, our results show that selective experience replay, when suitable selection algorithms are employed, can prevent catastrophic forgetting.

Downloads

Published

2018-04-29

How to Cite

Isele, D., & Cosgun, A. (2018). Selective Experience Replay for Lifelong Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). https://doi.org/10.1609/aaai.v32i1.11595