学习学习的时间：持续学习中的重放调度
Learn the Time to Learn: Replay Scheduling in Continual Learning
AI总结：
针对处理时间受限下持续学习中的重放调度问题，提出通过蒙特卡洛树搜索和强化学习学习重放调度策略，在不增加计算成本下提升了泛化能力并优于固定策略。
摘要：
已知在持续学习场景中，重放方法能有效缓解灾难性遗忘，尽管其对历史数据的访问受限。然而，在许多真实世界场景中，存储历史数据的成本很低，但由于处理时间限制，重放所有历史数据通常不可行。在此类场景中，我们提出持续学习系统应该学习学习的时间，并调度在不同时间步重放哪些任务。我们首先使用蒙特卡洛树搜索找到合适的重放调度，证明了我们提议的益处，并表明在不同的持续学习设置中，与各种重放方法结合时，所找到的重放调度优于固定调度策略。此外，我们提出了一个用强化学习学习重放调度策略的框架。我们表明，与同等重放所有已见任务相比，学习到的策略能在新的持续学习场景中更好地泛化，且不增加计算成本。我们的研究揭示了在持续学习中学习学习的时间的重要性，使当前研究更贴近真实世界需求。
英文摘要：
Replay methods are known to be successful at mitigating catastrophic forgetting in continual learning scenarios despite having limited access to historical data. However, storing historical data is cheap in many real-world settings, yet replaying all historical data is often prohibited due to processing time constraints. In such settings, we propose that continual learning systems should learn the time to learn and schedule which tasks to replay at different time steps. We first demonstrate the benefits of our proposal by using Monte Carlo tree search to find a proper replay schedule, and show that the found replay schedules can outperform fixed scheduling policies when combined with various replay methods in different continual learning settings. Additionally, we propose a framework for learning replay scheduling policies with reinforcement learning. We show that the learned policies can generalize better in new continual learning scenarios compared to equally replaying all seen tasks, without added computational cost. Our study reveals the importance of learning the time to learn in continual learning, which brings current research closer to real-world needs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
