Measuring Difficulty of Novelty Reaction
This addresses the challenge of systematically training and evaluating AI systems for real-world deployment where sudden changes occur, though it is incremental as it builds on existing novelty reaction concepts.
The paper tackles the problem of measuring how difficult it is for AI systems to react to unexpected changes in open-world environments, proposing a method to approximate this difficulty and showing alignment with evaluations of novelty-robust AI agents.
Current AI systems are designed to solve close-world problems with the assumption that the underlying world is remaining more or less the same. However, when dealing with real-world problems such assumptions can be invalid as sudden and unexpected changes can occur. To effectively deploy AI-powered systems in the real world, AI systems should be able to deal with open-world novelty quickly. Inevitably, dealing with open-world novelty raises an important question of novelty difficulty. Knowing whether one novelty is harder to deal with than another, can help researchers to train their systems systematically. In addition, it can also serve as a measurement of the performance of novelty robust AI systems. In this paper, we propose to define the novelty reaction difficulty as a relative difficulty of performing the known task after the introduction of the novelty. We propose a universal method that can be applied to approximate the difficulty. We present the approximations of the difficulty using our method and show how it aligns with the results of the evaluation of AI agents designed to deal with novelty.