Interactive Teaching Algorithms for Inverse Reinforcement Learning
Interactive Teaching Algorithms for Inverse Reinforcement Learning
Parameswaran Kamalaruban, Rati Devidze, Volkan Cevher, Adish Singla
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
Main track. Pages 2692-2700.
https://doi.org/10.24963/ijcai.2019/374
We study the problem of inverse reinforcement learning (IRL) with the added twist that the learner is assisted by a helpful teacher. More formally, we tackle the following algorithmic question: How could a teacher provide an informative sequence of demonstrations to an IRL learner to speed up the learning process? We present an interactive teaching framework where a teacher adaptively chooses the next demonstration based on learner's current policy. In particular, we design teaching algorithms for two concrete settings: an omniscient setting where a teacher has full knowledge about the learner's dynamics and a blackbox setting where the teacher has minimal knowledge. Then, we study a sequential variant of the popular MCE-IRL learner and prove convergence guarantees of our teaching algorithm in the omniscient setting. Extensive experiments with a car driving simulator environment show that the learning progress can be speeded up drastically as compared to an uninformative teacher.
Keywords:
Machine Learning: Reinforcement Learning
Humans and AI: Computer-Aided Education