发现强化学习会像人一样遗忘旧任务，但人类防忘方法在模型上效果有限。
Task Scheduling & Forgetting in Multi-Task Reinforcement Learning
- 对比人类与强化学习的遗忘曲线，发现行为相似。
- 类Leitner记忆法在模型上无法有效防止任务遗忘。
- 因任务间学习不对称，传统复习策略不适用。
强化学习（RL）智能体在训练新任务时会遗忘旧任务，这与人类的遗忘现象类似。本文研究了人类与RL智能体在多任务学习中的遗忘行为共性，并测试来自学习理论的遗忘预防措施在RL中的适用性。实验表明，许多情况下RL智能体表现出与人类相似的遗忘曲线。尽管Leitner或SuperMemo等方法能有效缓解人类遗忘，但在强化学习中效果不佳。我们识别出主要原因：任务间存在不对称的学习与保留模式，现有基于留存率或性能的课程设计策略无法捕捉这种差异。
原文摘要 · Abstract (English)
Reinforcement learning (RL) agents can forget tasks they have previously been trained on. There is a rich body of work on such forgetting effects in humans. Therefore we look for commonalities in the forgetting behavior of humans and RL agents across tasks and test the viability of forgetting prevention measures from learning theory in RL. We find that in many cases, RL agents exhibit forgetting curves similar to those of humans. Methods like Leitner or SuperMemo have been shown to be effective at counteracting human forgetting, but we demonstrate they do not transfer as well to RL. We identify a likely cause: asymmetrical learning and retention patterns between tasks that cannot be captured by retention-based or performance-based curriculum strategies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。