Lipschitz Lifelong Reinforcement Learning
Abstract
We 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 (MDPs) 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.
Cite
@article{arxiv.2001.05411,
title = {Lipschitz Lifelong Reinforcement Learning},
author = {Erwan Lecarpentier and David Abel and Kavosh Asadi and Yuu Jinnai and Emmanuel Rachelson and Michael L. Littman},
journal= {arXiv preprint arXiv:2001.05411},
year = {2021}
}
Comments
In proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI 2021), 21 pages, 11 figures