Free-Energy-Gated Plasticity for Real-Time Online Motor Learning in Physical Human--Robot Interaction
产业动态
来源：arXiv cs.RO发布时间待核实
arXiv:2608.23000v1 Announce Type: new Abstract: Fully online embodied learning requires synaptic adaptation to acquire new behaviors while preserving previously learned dynamics during ongoing interaction. We extend the Predictive-Coding-inspired Variational Recurrent Neural Network (PV-RNN) to continuously adapt its synaptic weights and propose Free-Energy-Gated Plasticity (FEGP), which regulates the effective learning rate according to variational free energy.