Lipschitz Lifelong Reinforcement Learning
Keywords:Reinforcement Learning, Transfer/Adaptation/Multi-task/Meta/Automated Learning
AbstractWe consider the problem of knowledge transfer when an agent is facing a series of Reinforcement Learning (RL) tasks. We introduce a novel metric between Markov Decision Processes and establish that close MDPs have close optimal value functions. Formally, the optimal value functions are Lipschitz continuous with respect to the tasks space. These theoretical results lead us to a value-transfer method for Lifelong RL, which we use to build a PAC-MDP algorithm with improved convergence rate. Further, we show the method to experience no negative transfer with high probability. We illustrate the benefits of the method in Lifelong RL experiments.
How to Cite
Lecarpentier, E., Abel, D., Asadi, K., Jinnai, Y., Rachelson, E., & Littman, M. L. (2021). Lipschitz Lifelong Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 35(9), 8270-8278. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17006
AAAI Technical Track on Machine Learning II