Monte-Carlo Exploration for Deterministic Planning
Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence. Pages 1766-1770.
Abstract
Search methods based on Monte-Carlo simulation have recently led to breakthrough performance improvements in difficult game-playing domains such as Go and General Game Playing. Monte-Carlo Random Walk (MRW) planning applies Monte-Carlo ideas to deterministic classical planning. In the forward chaining planner Arvand, Monte-Carlo random walks are used to explore the local neighborhood of a search state for action selection. In contrast to the stochastic local search approach used in the recent planner Identidem, random walks yield a larger and unbiased sample of the search neighborhood, and require state evaluations only at the endpoints of each walk. On IPC-4 competition problems, the performance of Arvand is competitive with state of the art systems.Hootan Nakhost, Martin Müller
@inproceedings{ijcai2009p294,
title = {Monte-Carlo Exploration for Deterministic Planning},
author = {Nakhost, Hootan and Müller, Martin},
booktitle = {Proceedings of the Twenty-First International Joint Conference on
Artificial Intelligence, {IJCAI-09}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Hiroaki Kitano},
pages = {1766--1770},
year = {2009},
url = {https://ijcai.org/proceedings/2009/294},
}
TY - CPAPER TI - Monte-Carlo Exploration for Deterministic Planning AU - Nakhost, Hootan AU - Müller, Martin T2 - Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence, IJCAI-09 PB - International Joint Conferences on Artificial Intelligence PY - 2009 SP - 1766 EP - 1770 UR - https://ijcai.org/proceedings/2009/294 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
