Scalable Safe Policy Improvement via Monte Carlo Tree Search
Alberto Castellini (University of Verona)
Federico Bianchi (University of Verona)
Edoardo Zorzi (University of Verona, ETH Zürich)
Thiago D. Simão (Radboud Universiteit Nijmegen)
Alessandro Farinelli (University of Verona)
M. T.J. Spaan (TU Delft - Algorithmics)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Algorithms for safely improving policies are important to deploy reinforcement learning approaches in real-world scenarios. In this work, we propose an algorithm, called MCTS-SPIBB, that computes safe policy improvement online using a Monte Carlo Tree Search based strategy. We theoretically prove that the policy generated by MCTS-SPIBB converges, as the number of simulations grows, to the optimal safely improved policy generated by Safe Policy Improvement with Baseline Bootstrapping (SPIBB), a popular algorithm based on policy iteration. Moreover, our empirical analysis performed on three standard benchmark domains shows that MCTS-SPIBB scales to significantly larger problems than SPIBB because it computes the policy online and locally, i.e., only in the states actually visited by the agent.