DeepAI AI Chat
Log In Sign Up

Combinatorial Multi-armed Bandits for Real-Time Strategy Games

10/13/2017
by   Santiago Ontañón, et al.
Drexel University
0

Games with large branching factors pose a significant challenge for game tree search algorithms. In this paper, we address this problem with a sampling strategy for Monte Carlo Tree Search (MCTS) algorithms called naïve sampling, based on a variant of the Multi-armed Bandit problem called Combinatorial Multi-armed Bandits (CMAB). We analyze the theoretical properties of several variants of naïve sampling, and empirically compare it against the other existing strategies in the literature for CMABs. We then evaluate these strategies in the context of real-time strategy (RTS) games, a genre of computer games characterized by their very large branching factors. Our results show that as the branching factor grows, naïve sampling outperforms the other sampling strategies.

READ FULL TEXT

page 1

page 2

page 3

page 4

07/17/2017

Online Multi-Armed Bandit

We introduce a novel variant of the multi-armed bandit problem, in which...
02/10/2021

Regression Oracles and Exploration Strategies for Short-Horizon Multi-Armed Bandits

This paper explores multi-armed bandit (MAB) strategies in very short ho...
06/30/2015

Scalable Discrete Sampling as a Multi-Armed Bandit Problem

Drawing a sample from a discrete distribution is one of the building com...
04/20/2018

Delegating via Quitting Games

Delegation allows an agent to request that another agent completes a tas...
05/15/2018

Graph Signal Sampling via Reinforcement Learning

We formulate the problem of sampling and recovering clustered graph sign...
02/15/2023

Genetic multi-armed bandits: a reinforcement learning approach for discrete optimization via simulation

This paper proposes a new algorithm, referred to as GMAB, that combines ...
10/11/2019

Nonparametric Bayesian multi-armed bandits for single cell experiment design

The problem of maximizing cell type discovery under budget constraints i...