提出可动态组合策略的模块化网络，解决持续强化学习中的遗忘问题。
Self-Composing Policies for Scalable Continual Reinforcement Learning
- 模块化结构支持选择性组合旧策略与新策略
- 参数量随任务数线性增长，性能优于基线方法
- 适合需要长期学习与迁移的任务场景
本文提出一种可扩展的模块化神经网络架构，天然避免持续强化学习中的灾难性遗忘和干扰。每个模块的结构允许选择性地组合先前策略与自身内部策略，加速当前任务的学习。与以往的生长型神经网络方法不同，该方法的参数量随任务数线性增长，且不牺牲可塑性以实现扩展。在基准连续控制和视觉任务上的实验表明，该方法在知识迁移和性能上均优于现有方法。
原文摘要 · Abstract (English)
This work introduces a growable and modular neural network architecture that naturally avoids catastrophic forgetting and interference in continual reinforcement learning. The structure of each module allows the selective combination of previous policies along with its internal policy, accelerating the learning process on the current task. Unlike previous growing neural network approaches, we show that the number of parameters of the proposed approach grows linearly with respect to the number of tasks, and does not sacrifice plasticity to scale. Experiments conducted in benchmark continuous control and visual problems reveal that the proposed approach achieves greater knowledge transfer and performance than alternative methods.
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。