A case-based reasoning approach to learning state-based behavior
Learning from Observation involves creating agents that observe experts performing tasks and imitate them. Case-Based Reasoning (CBR) is a tool that can be used for this purpose. Regular CBR can only learn memoryless behavior: behavior that doesn't rely on the past. Temporal Backtracking (TB) is an approach to learning state-based behavior that uses re-cency as its inductive bias, which may or may not be relevant to the agent behavior. We show how TB can be viewed as a particular case of a more generalized case-based approach to learning state-based behavior that can accommodate other inductive biases. We then propose five alternative similarity metrics to learn three different state-based behaviors in a 2D vacuum cleaner domain, and compare their performance to the TB algorithm's performance. We show that none of the proposed metrics (nor TB) is a one-size-fits all algorithm for learning state-based behavior.
|Conference||31st International Florida Artificial Intelligence Research Society Conference, FLAIRS 2018|
Sacha, A. (Amrik), Gunaratne, E. (Elapata), Esfandiari, B, & Fawaz, A. (Ali). (2018). A case-based reasoning approach to learning state-based behavior. In Proceedings of the 31st International Florida Artificial Intelligence Research Society Conference, FLAIRS 2018 (pp. 377–382).