Lifelong Inverse Reinforcement Learning

Advances in Neural Information Processing Systems (NeurIPS), 2018
PDF   Code   Video   Poster  

Abstract: 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.

Recommended citation:

author = {Mendez-Mendez, Jorge and Shivkumar, Shashank and Eaton, Eric},
booktitle = {Advances in Neural Information Processing Systems 31 (NeurIPS-18)},
title = {Lifelong Inverse Reinforcement Learning},
year = {2018}