Despite its omnipresence in robotics application, the nature of spatial knowledge and the mechanisms that underlie its emergence in autonomous agents are still poorly understood. Recent theoretical work suggests that the concept of space can be grounded by capturing invariants induced by the structure of space in an agent's raw sensorimotor experience. Moreover, it is hypothesized that capturing these invariants is beneficial for a naive agent trying to predict its sensorimotor experience. Under certain exploratory conditions, spatial representations should thus emerge as a byproduct of learning to predict. We propose a simple sensorimotor predictive scheme, apply it to different agents and types of exploration, and evaluate the pertinence of this hypothesis. We show that a naive agent can capture the topology and metric regularity of its spatial configuration without any a priori knowledge, nor extraneous supervision.
Emergence of Nonequilibrium Latent Cycles in Unsupervised Generative Modeling
Department of Physics;Astronomy, University of Padova, Via Marzolo 8, I-35131 Padova, Italy;LPTMS, CNRS, Universit\'e Paris-Saclay, 91405, Orsay, France
Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning
Zhejiang University(浙江大学);Westlake University(西湖大学);UC Berkeley(加州大学伯克利分校);Institute of Advanced Technology, Westlake Institute for Advanced Study(西湖高等研究院前沿技术研究所)
'Place-cell' emergence and learning of invariant data with restricted Boltzmann machines: breaking and dynamical restoration of continuous symmetries in the weight space
LPENS(巴黎高等师范学院物理实验室);Ecole Normale Supérieure(巴黎高等师范学院);PSL Research(PSL研究大学);Blavatnik School of Computer Science(布拉瓦特尼克计算机科学学院);Tel Aviv University(特拉维夫大学)