Monte Carlo Tree Search with Boltzmann Exploration

arXiv:2404.07732v1 Announce Type: cross
Abstract: Monte-Carlo Tree Search (MCTS) methods, such as Upper Confidence Bound applied to Trees (UCT), are instrumental to automated planning techniques. However, UCT can be slow to explore an optimal action when it initially appears inferior to other actions. Maximum ENtropy Tree-Search (MENTS) incorporates the maximum entropy principle into an MCTS approach, utilising Boltzmann policies to sample actions, naturally encouraging more exploration. In this paper, we highlight a major limitation of MENTS: optimal actions for the …

abstract arxiv automated boltzmann confidence cs.ai cs.lg entropy exploration explore however monte-carlo planning search tree trees type