发表机构
Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对多任务强化学习的任务间干扰问题，提出含特征选择器与任务调度器的T3S框架，在机器人操作任务上性能优于现有最优多任务强化学习算法。
AI 中文摘要
多任务强化学习（MTRL）是一种同时训练多个任务的技术，现有研究通常通过跨任务共享参数来训练单一模型解决不同任务。然而，这类方法面临任务间干扰问题，因为未明确哪些参数应跨任务共享，大幅降低了学习效率。为解决这些问题，我们提出一种名为任务特定特征选择器与调度器（T3S）的新型MTRL框架，它由两个组件构成：特征选择器与任务调度器。具体而言，特征选择器采用超网络构建任务特定软掩码，该掩码可应用于全局共享表示以生成任务特定特征；任务调度器通过两个指标选择学习任务，其中选择概率与任务进度（如成功率）及任务学习速度成反比。实验结果表明，在各类机器人操作任务上，T3S始终优于当前最优的MTRL算法。
英文摘要
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.
Comments8 pages, 7 figures, 4 tables. Published in the 2023 International Joint Conference on Neural Networks (IJCNN)
Journal ref2023 International Joint Conference on Neural Networks (IJCNN), pp. 1-8, 2023
DOI：10.1109/IJCNN54540.2023.10191536
