Artificial intelligence publications

In this paper, we expand PIMT to a lifted version that also processes random functions and relations.

We present an approach that converts human advice into synthetic or imagined training experiences, serving to scaffold the low-level representations of simple, reactive learning systems such as reinforcement learners.

We consider the use of an advanced cryptographic technique called secure multi-party computation to enable coalition members to achieve joint objectives while still meeting privacy requirements.

The framework uses introspective analysis of an agent’s history of interaction with its environment to extract several interestingness elements regarding its behavior.

We present an explanation framework based on the notion of explanation drivers —i.e., the intent or purpose behind agent explanations. We focus on explanations meant to reconcile expectation violations and…