# Selective Experience Replay for Lifelong Learning Source: [Selective Experience Replay for Lifelong Learning]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:55:10.976Z Authors: David Isele, Akansel Cosgun Published: 2018-02-28T06:02:31.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Online Continual Self-Supervised Learning on iNaturalist](): Online Continual Self-Supervised Learning; iNaturalist; Final Accuracy: 43.91. ## Original sources and implementation [Original paper]() [PDF]()