This year’s workshop is the inaugural edition of SPiRL.

Connections to Prior Workshops

The concept of structure and priors in reinforcement learning follows from a number of related workshops that have been successful at past conferences such as NeurIPS and ICML. In particular, besides workshops on recent advances in reinforcement learning methods (such as the Workshop on “Deep Reinforcement Learning” at NeurIPS 2016–2018), we take inspiration from the following workshops:

In contrast to these workshops, rather than solely exploring different methods for learning and designing structure and priors in reinforcement learning, we intend this workshop to be a cross-disciplinary discussion of the utility, necessity, and formulation of structure and priors.