Proceedings of the Annual Meeting of the Cognitive Science Society

Play and curiosity are unmistakable signatures of an active mind. It is perhaps unsurprising then, that recent advances in machine learning and robotics have used algorithmic approximations of curiosity to build artificial agents that can intelligently explore their environments, learn more efficiently, and acquire more generalizable skills (e.g. Chitnis et al., 2020; Lynch et al., 2020; Forestier et al., 2017).