Saved in:
Bibliographic Details
Main Authors: Schramm, Liam, Boularias, Abdeslam
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.05511
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914861185761280
author Schramm, Liam
Boularias, Abdeslam
author_facet Schramm, Liam
Boularias, Abdeslam
contents Monte Carlo tree search (MCTS) has been successful in a variety of domains, but faces challenges with long-horizon exploration when compared to sampling-based motion planning algorithms like Rapidly-Exploring Random Trees. To address these limitations of MCTS, we derive a tree search algorithm based on policy optimization with state occupancy measure regularization, which we call {\it Volume-MCTS}. We show that count-based exploration and sampling-based motion planning can be derived as approximate solutions to this state occupancy measure regularized objective. We test our method on several robot navigation problems, and find that Volume-MCTS outperforms AlphaZero and displays significantly better long-horizon exploration properties.
format Preprint
id arxiv_https___arxiv_org_abs_2407_05511
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Provably Efficient Long-Horizon Exploration in Monte Carlo Tree Search through State Occupancy Regularization
Schramm, Liam
Boularias, Abdeslam
Machine Learning
Robotics
Monte Carlo tree search (MCTS) has been successful in a variety of domains, but faces challenges with long-horizon exploration when compared to sampling-based motion planning algorithms like Rapidly-Exploring Random Trees. To address these limitations of MCTS, we derive a tree search algorithm based on policy optimization with state occupancy measure regularization, which we call {\it Volume-MCTS}. We show that count-based exploration and sampling-based motion planning can be derived as approximate solutions to this state occupancy measure regularized objective. We test our method on several robot navigation problems, and find that Volume-MCTS outperforms AlphaZero and displays significantly better long-horizon exploration properties.
title Provably Efficient Long-Horizon Exploration in Monte Carlo Tree Search through State Occupancy Regularization
topic Machine Learning
Robotics
url https://arxiv.org/abs/2407.05511