T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler

Abstract: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.

8 pages, 7 figures, 4 tables. Published in the 2023 International Joint Conference on Neural Networks (IJCNN)

Machine Learning (cs.LG)

arXiv:2608.30765 [cs.LG]

(or arXiv:2608.30765v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2608.30765 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

2023 International Joint Conference on Neural Networks (IJCNN), pp. 1-8, 2023

https://doi.org/10.1109/IJCNN54540.2023.10191536 Focus to learn more DOI(s) linking to related resources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.