English

Monte-Carlo Tree Search for Policy Optimization

Machine Learning 2019-12-24 v1 Artificial Intelligence Machine Learning

Abstract

Gradient-based methods are often used for policy optimization in deep reinforcement learning, despite being vulnerable to local optima and saddle points. Although gradient-free methods (e.g., genetic algorithms or evolution strategies) help mitigate these issues, poor initialization and local optima are still concerns in highly nonconvex spaces. This paper presents a method for policy optimization based on Monte-Carlo tree search and gradient-free optimization. Our method, called Monte-Carlo tree search for policy optimization (MCTSPO), provides a better exploration-exploitation trade-off through the use of the upper confidence bound heuristic. We demonstrate improved performance on reinforcement learning tasks with deceptive or sparse reward functions compared to popular gradient-based and deep genetic algorithm baselines.

Keywords

Cite

@article{arxiv.1912.10648,
  title  = {Monte-Carlo Tree Search for Policy Optimization},
  author = {Xiaobai Ma and Katherine Driggs-Campbell and Zongzhang Zhang and Mykel J. Kochenderfer},
  journal= {arXiv preprint arXiv:1912.10648},
  year   = {2019}
}

Comments

IJCAI 2019

R2 v1 2026-06-23T12:54:13.037Z