TY - JOUR
T1 - Methods and Mechanisms for Interactive Novelty Handling in Adversarial Environments
AU - Thai, Tung
AU - Verma, Mudit
AU - Soni, Utkarsh
AU - Gopalakrishnan, Sriram
AU - Shen, Ming
AU - Garg, Mayank
AU - Kalani, Ayush
AU - Vaidya, Nakul
AU - Varshney, Neeraj
AU - Baral, Chitta
AU - Kambhampati, Subbarao
AU - Sinapov, Jivko
AU - Scheutz, Matthias
N1 - Funding Information:
This work was funded in part by DARPA grant W911NF-20-2-0006. We would like to thank Mayank Kejriwal, Shilpa Thomas, Min-Hsueh Chiu and other members of the University of Southern California team for the Monopoly simulator and agent evaluation.
Publisher Copyright:
© 2023 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
PY - 2023
Y1 - 2023
N2 - Learning to detect, characterize and accommodate novelties is a challenge that agents operating in open-world domains need to address to achieve satisfactory task performance. We sketch general methods for detecting and characterizing different types of novelties, and for building an appropriate adaptive model to accommodate them utilizing logical representations and reasoning methods in stochastic partially observable multi-agent environments. We also briefly report results from evaluations of our algorithms in the game domain of Monopoly. The results show high novelty detection and accommodation rates.
AB - Learning to detect, characterize and accommodate novelties is a challenge that agents operating in open-world domains need to address to achieve satisfactory task performance. We sketch general methods for detecting and characterizing different types of novelties, and for building an appropriate adaptive model to accommodate them utilizing logical representations and reasoning methods in stochastic partially observable multi-agent environments. We also briefly report results from evaluations of our algorithms in the game domain of Monopoly. The results show high novelty detection and accommodation rates.
KW - Adaptive Multiagent Systems
KW - Agent Architecture
KW - Open-world AI
UR - http://www.scopus.com/inward/record.url?scp=85171285972&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85171285972&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85171285972
SN - 1548-8403
VL - 2023-May
SP - 2385
EP - 2387
JO - Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
JF - Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
T2 - 22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023
Y2 - 29 May 2023 through 2 June 2023
ER -