File(s) under embargo
Selective experience replay for lifelong learning
conference contributionposted on 2023-10-02, 22:58 authored by D Isele, Akan CosgunAkan Cosgun
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.
LocationLA, New Orleans
Title of proceedings32nd AAAI Conference on Artificial Intelligence, AAAI 2018
Event32nd AAAI Conference on Artificial Intelligence / 30th Innovative Applications of Artificial Intelligence Conference / 8th AAAI Symposium on Educational Advances in Artificial Intelligence
PublisherASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE
Place of publicationNew York, N.Y.
SeriesAAAI Conference on Artificial Intelligence
CategoriesNo categories selected