Probabilistic Inference-based Reinforcement Learning

Abstract

We introduce probabilistic inference-based reinforcement learning (PIReL), an approach to solve decision making problems by treating them as probabilistic inference tasks. Unlike classical reinforcement learning, which requires explicit reward functions, in PIReL they are implied by probabilistic assumptions of the model. This would enable a fundamental way to design the reward function by model selection as well as bring the potential to apply existing probabilistic modeling techniques to reinforcement learning problems.

Bert de Vries

Professor

I am a professor at TU Eindhoven and team leader of BIASlab.

Tjalling Tjalkens

Former professor

Former researcher at BIASlab.