The ability of AI agents and architectures to detect and adapt to sudden changes in their environments remains an outstand- ing challenge. In the context of multi-agent games, the agent may face novel situations where the rules of the game, the available actions, the environment dynamics, the behavior of other agents, as well as the agent’s goals suddenly change. In this paper, we introduce an architecture that allows agents to detect novelties, characterize those novelties, and build an appropriate adaptive model to accommodate them. Our agent utilizes logic and reasoning (specifically, Answer Set Pro- gramming) to characterize novelties into different categories, as to enable the agent to adapt to the novelty while maintain- ing high performance in the game. We demonstrate the effec- tiveness of the proposed agent architecture in a multi-agent imperfect information board game, Monopoly. We measure the success of the architecture by comparing our method to heuristics, and vanilla Monte-Carlo Tree Search approaches. Our results indicate precise novelty detection, and significant improvements in the performance of agents utilizing the nov- elty handling architecture.
@inproceedings{tungetal22aaaiss,
title={An Architecture for Novelty Handling in a Multi-Agent Stochastic Environment: Case Study in Open-World Monopoly.},
author={Thai, Tung and Shen, Ming and Varshney, Neeraj and Gopalakrishnan, Sriram and Soni, Utkarsh and Baral, Chitta and Sinapov, Jivko and Scheutz, Matthias},
year={2022},
booktitle={Proceedings of AAAI Spring Symposium on Designing Artificial Intelligence for Open Worlds.},
url={https://hrilab.tufts.edu/publications/tungetal22aaaiss.pdf}
}