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

06/29/2021
by   Ricardo Quinteiro, et al.
0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

06/08/2020

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

Monte-Carlo planning, as exemplified by Monte-Carlo Tree Search (MCTS), ...
08/18/2011

Doing Better Than UCT: Rational Monte Carlo Sampling in Trees

UCT, a state-of-the art algorithm for Monte Carlo tree sampling (MCTS), ...
03/09/2020

Convex Hull Monte-Carlo Tree Search

This work investigates Monte-Carlo planning for agents in stochastic env...
08/09/2014

Selecting Computations: Theory and Applications

Sequential decision problems are often approximately solvable by simulat...
01/08/2019

Solar-Sail Trajectory Design for Multiple Near Earth Asteroid Exploration Based on Deep Neural Networks

In the preliminary trajectory design of the multi-target rendezvous prob...
01/08/2019

Solar-Sail Trajectory Design of Multiple Near Earth Asteroids Exploration Based on Deep Neural Network

In the preliminary trajectory design of the multi-target rendezvous prob...
09/06/2019

Efficient Multivariate Bandit Algorithm with Path Planning

In this paper, we solve the arms exponential exploding issue in multivar...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.