Representation Edit Distance as a Measure of Novelty
This work addresses the challenge of quantifying novelty adaptation for agents, but it appears incremental as it builds on existing concepts of representation and edit distance.
The paper tackles the problem of measuring adaptation difficulty to novelty by proposing Representation Edit Distance (RED) as a metric based on editing skill programs, with results demonstrated through notional examples.
Adaptation to novelty is viewed as learning to change and augment existing skills to confront unfamiliar situations. In this paper, we propose that the amount of editing of an effective representation (the Representation Edit Distance or RED) used in a set of skill programs in an agent's mental model is a measure of difficulty for adaptation to novelty. The RED is an intuitive approximation to the change in information content in bit strings measured by comparing pre-novelty and post-novelty skill programs. We also present some notional examples of how to use RED for predicting difficulty.