Generalized Nested Rollout Policy Adaptation

2020/03/22 by Cazenave, Tristan · 3 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2003.10024

Abstract

Nested Rollout Policy Adaptation (NRPA) is a Monte Carlo search algorithm for single player games. In this paper we propose to generalize NRPA with a temperature and a bias and to analyze theoretically the algorithms. The generalized algorithm is named GNRPA. Experiments show it improves on NRPA for different application domains: SameGame and the Traveling Salesman Problem with Time Windows.

Cited by

• Pareto-NRPA: A Novel Monte-Carlo Search Algorithm for Multi-Objective Optimization
• Adaptive Bias Generalized Rollout Policy Adaptation on the Flexible Job-Shop Scheduling Problem
• Eterna is Solved
• The Montparnasse Algorithm for RNA Design

Related

• Generalized Nested Rollout Policy Adaptation with Limited Repetitions
• Single-Agent Optimization Through Policy Iteration Using Monte-Carlo\n Tree Search
• Monte Carlo Rollout Policy for Recommendation Systems with Dynamic User\n Behavior
• Multiple Policy Value Monte Carlo Tree Search
• The Update-Equivalence Framework for Decision-Time Planning