Integrating Planning, Execution and Monitoring in the presence of Open World Novelties: Case Study of an Open World Monopoly Solver
This addresses the problem of open-world unpredictability for AI agents in multi-agent domains, though it is incremental as part of a broader program.
The paper tackles the challenge of handling unknown novelties in the adversarial game of Monopoly by developing an agent that adapts its policy online, resulting in it being the best-performing agent in the DARPA-SAILON program evaluation.
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.