Integrating Planning, Execution and Monitoring in the presence of Open World Novelties: Case Study of an Open World Monopoly Solver

TL;DR

This paper presents an adaptive agent for Monopoly that integrates planning, execution, and monitoring to handle unpredictability and novelties, demonstrating superior performance in DARPA-SAILON evaluations.

Contribution

The paper introduces a novel adaptive agent that manages open-world novelties in Monopoly by online policy adaptation, outperforming existing agents.

Findings

Agent outperformed others in DARPA-SAILON evaluations

Successfully handled unpredictability and novelties in gameplay

Demonstrated effective online policy adaptation

Abstract

The game of monopoly is an adversarial multi-agent domain where there is no fixed goal other than to be the last player solvent, There are useful subgoals like monopolizing sets of properties, and developing them. There is also a lot of randomness from dice rolls, card-draws, and adversaries' strategies. This unpredictability is made worse when unknown novelties are added during gameplay. Given these challenges, Monopoly was one of the test beds chosen for the DARPA-SAILON program which aims to create agents that can detect and accommodate novelties. To handle the game complexities, we developed an agent that eschews complete plans, and adapts it's policy online as the game evolves. In the most recent independent evaluation in the SAILON program, our agent was the best performing agent on most measures. We herein present our approach and results.