Lifelong Inverse Reinforcement Learning
This addresses the burden on users for versatile agents learning many tasks, though it is incremental as it builds on existing inverse reinforcement learning methods.
The paper tackles the challenge of reducing the number of demonstrations needed for learning multiple tasks from demonstration by introducing lifelong learning from demonstration, which accelerates new task learning through knowledge transfer from previous tasks, resulting in reduced demonstration requirements.
Methods for learning from demonstration (LfD) have shown success in acquiring behavior policies by imitating a user. However, even for a single task, LfD may require numerous demonstrations. For versatile agents that must learn many tasks via demonstration, this process would substantially burden the user if each task were learned in isolation. To address this challenge, we introduce the novel problem of lifelong learning from demonstration, which allows the agent to continually build upon knowledge learned from previously demonstrated tasks to accelerate the learning of new tasks, reducing the amount of demonstrations required. As one solution to this problem, we propose the first lifelong learning approach to inverse reinforcement learning, which learns consecutive tasks via demonstration, continually transferring knowledge between tasks to improve performance.