3 papers
cs.RO2025
E-SDS: Environment-aware See it, Do it, Sorted - Automated Environment-Aware Reinforcement Learning for Humanoid Locomotion
Enis Yalcin, Joshua O'Hara, Maria Stamatopoulou +2
Vision-language models (VLMs) show promise in automating reward design in humanoid locomotion, which could eliminate the need for tedious manual engineering. However, current VLM-b…
cs.NE2025
Self-Motivated Growing Neural Network for Adaptive Architecture via Local Structural Plasticity
Yiyang Jia, Chengxu Zhou
Control policies are often implemented with fixed-capacity multilayer perceptrons trained by backpropagation, which require architecture selection in advance and cannot adapt their…
cs.LG2024
PAL -- Parallel active learning for machine-learned potentials
Chen Zhou, Marlen Neubert, Yuri Koide +5
Constructing datasets representative of the target domain is essential for training effective machine learning models. Active learning (AL) is a promising method that iteratively e…