Monte Carlo Tree Search with Scalable Simulation Periods for Continuously Running Tasks

TL;DR

This paper introduces a method to adapt Monte Carlo Tree Search for continuously running tasks by dynamically adjusting simulation time, leading to improved decision-making in environments with continuous and discrete actions.

Contribution

The paper extends the HOOT method to optimize simulation time as a decision variable, enhancing MCTS performance in continuous decision environments.

Findings

Outperforms traditional MCTS in continuous decision tasks

Improves MCTS performance in most ALE tasks

Effectively balances simulation time and action selection

Abstract

Monte Carlo Tree Search (MCTS) is particularly adapted to domains where the potential actions can be represented as a tree of sequential decisions. For an effective action selection, MCTS performs many simulations to build a reliable tree representation of the decision space. As such, a bottleneck to MCTS appears when enough simulations cannot be performed between action selections. This is particularly highlighted in continuously running tasks, for which the time available to perform simulations between actions tends to be limited due to the environment's state constantly changing. In this paper, we present an approach that takes advantage of the anytime characteristic of MCTS to increase the simulation time when allowed. Our approach is to effectively balance the prospect of selecting an action with the time that can be spared to perform MCTS simulations before the next action selection. For that, we considered the simulation time as a decision variable to be selected alongside an action. We extended the Hierarchical Optimistic Optimization applied to Tree (HOOT) method to adapt our approach to environments with a continuous decision space. We evaluated our approach for environments with a continuous decision space through OpenAI gym's Pendulum and Continuous Mountain Car environments and for environments with discrete action space through the arcade learning environment (ALE) platform. The evaluation results show that, with variable simulation times, the proposed approach outperforms the conventional MCTS in the evaluated continuous decision space tasks and improves the performance of MCTS in most of the ALE tasks.