@inproceedings{grill2020monte-carlo,
abstract = {The combination of Monte-Carlo tree search (MCTS) with deep reinforcement learning has led to groundbreaking results in artificial intelligence. However, AlphaZero, the current state-of-the-art MCTS algorithm still relies on handcrafted heuristics that are only partially understood. In this paper, we show that AlphaZero's search heuristic, along with other common ones, can be interpreted as an approximation to the solution of a specific regularized policy optimization problem. With this insight, we propose a variant of AlphaZero which uses the exact solution to this policy optimization problem, and show experimentally that it reliably outperforms the original algorithm in multiple domains.},
author = {Grill, Jean-Bastien and Altch{\'{e}}, Florent and Tang, Yunhao and Hubert, Thomas and Valko, Michal and Antonoglou, Ioannis and Munos, R{\'{e}}mi},
booktitle = {International Conference on Machine Learning},
title = {{Monte-Carlo tree search as regularized policy optimization}},
year = {2020}
}