TPAL: an Assembly Language for Temporal Probabilistic Programming

Probabilistic programming is a powerful paradigm in the field of machine learning and artificial intelligence. The proposal studies how to efficiently extend probabilistic programming with temporal components. The goal is to develop TPAL, a temporal probabilistic assembly language that can be used as expressive yet efficient language to express planning problems in artificial intelligence. Ultimately we aim at deploying TPAL to the domain of cognitive robotics, where we have to deal with noisy sensor data in a dynamically changing world.

Keywords:probabilistic programming, probabilistic dynamics, assembly language, cognitive robotics

Disciplines:Artificial intelligence not elsewhere classified, Knowledge representation and reasoning, Machine learning and decision making, Adaptive agents and intelligent robotics