T3S通过动态选择任务和特征，提升多任务强化学习效率。
T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler
- 用超网络生成任务专属特征掩码，实现共享表征下的个性化特征提取。
- 按任务进展与学习速度反比选择训练任务，避免干扰并加速收敛。
- 在多种机器人操作任务中优于现有方法，适合复杂多任务场景应用。
多任务强化学习（MTRL）旨在同时训练多个任务，传统方法通过跨任务共享参数来统一模型，但存在任务间干扰问题，因未明确应共享哪些参数而显著降低学习效率。为此，本文提出新型MTRL框架T3S，包含特征选择器与任务调度器两部分：特征选择器利用超网络构建任务特定的软掩码，对全局共享表示进行调制以生成任务专属特征；任务调度器根据任务进展（如成功概率）和学习速度两个指标选择训练任务，选择概率与二者呈反比。实验表明，T3S在多种机器人操作任务上持续优于当前最优MTRL算法。
原文摘要 · Abstract (English)
Multi-task reinforcement learning (MTRL) is a technique to train multiple tasks simultaneously, where previous works usually train a single model to solve different tasks by sharing parameters across various tasks. However, these methods are faced with inter-task interference since what parameters should be shared across tasks is not addressed, dramatically reducing learning efficiency. To solve these problems, we propose a novel MTRL framework called Task-Specific feature Selector and Scheduler (T3S), which consists of two components: a feature selector and a task scheduler. Specifically, the feature selectors employ hypernetworks to construct task-specific soft masks, which can be applied by globally shared representation to construct task-specific features. The task scheduler selects tasks for learning through two metrics, where the selection probability is inversely proportional to task progress (e.g., success rate) and task learning speed. Experimental results show that T3S consistently outperforms the state-of-the-art MTRL algorithms on various robotics manipulation tasks.
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。