paper-with-me

홈 › Papers

Limited depth bandit-based strategy for Monte Carlo planning in continuous action spaces

2021-06-29 · Ricardo Quinteiro, Francisco S. Melo, Pedro A. Santos

This paper addresses the problem of optimal control using search trees. We start by considering multi-armed bandit problems with continuous action spaces and propose LD-HOO, a limited depth variant of the hierarchical optimistic optimization (HOO) algorithm. We provide a regret analysis for LD-HOO and show that, asymptotically, our algorithm exhibits the same cumulative regret as the original HOO while being faster and more memory efficient. We then propose a Monte Carlo tree search algorithm based on LD-HOO for optimal control problems and illustrate the resulting approach's application in several optimal control problems.

📄 PDF Abstract BibTeX arXiv:2106.15594

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Power Mean Estimation in Stochastic Monte-Carlo Tree_Search

2024-06-04 · Tuan Dam, Odalric-Ambrym Maillard, Emilie Kaufmann

Monte-Carlo Tree Search (MCTS) is a widely-used strategy for online planning that combines Monte-Carlo sampling with forward tree search. Its success relies on the Upper Confidence bound for Trees (UCT) algorithm, an ext…

Sequential Monte Carlo Bandits

2013-10-04 · Michael Cherkassky, Luke Bornn

In this paper we propose a flexible and efficient framework for handling multi-armed bandits, combining sequential Monte Carlo algorithms with hierarchical Bayesian modeling techniques. The framework naturally encompasse…

Multi-Armed Bandits

Monte Carlo Methods for the Game Kingdomino

2018-07-12 · Magnus Gedda, Mikael Z. Lagerkvist, Martin Butler

Kingdomino is introduced as an interesting game for studying game playing: the game is multiplayer (4 independent players per game); it has a limited game depth (13 moves per player); and it has limited but not insignifi…

Measurable Monte Carlo Search Error Bounds

2021-06-08 · John Mern, Mykel J. Kochenderfer

Monte Carlo planners can often return sub-optimal actions, even if they are guaranteed to converge in the limit of infinite samples. Known asymptotic regret bounds do not provide any way to measure confidence of a recomm…

POLY-HOOT: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis

2020-06-08 · NeurIPS 2020 12 · Weichao Mao, Kaiqing Zhang, Qiaomin Xie, Tamer Başar

Monte-Carlo planning, as exemplified by Monte-Carlo Tree Search (MCTS), has demonstrated remarkable performance in applications with finite spaces. In this paper, we consider Monte-Carlo planning in an environment with c…