Methods and Mechanisms for Interactive Novelty Handling in Adversarial Environments
This addresses the challenge of maintaining agent performance in dynamic, adversarial settings, though it appears incremental as it builds on existing novelty handling methods.
The paper tackles the problem of agents detecting and adapting to novelties in open-world environments, such as changes in rules or capabilities, and demonstrates high detection and accommodation rates in evaluations on the adversarial board game Monopoly.
Learning to detect, characterize and accommodate novelties is a challenge that agents operating in open-world domains need to address to be able to guarantee satisfactory task performance. Certain novelties (e.g., changes in environment dynamics) can interfere with the performance or prevent agents from accomplishing task goals altogether. In this paper, we introduce general methods and architectural mechanisms for detecting and characterizing different types of novelties, and for building an appropriate adaptive model to accommodate them utilizing logical representations and reasoning methods. We demonstrate the effectiveness of the proposed methods in evaluations performed by a third party in the adversarial multi-agent board game Monopoly. The results show high novelty detection and accommodation rates across a variety of novelty types, including changes to the rules of the game, as well as changes to the agent's action capabilities.