Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models
产业动态
来源：arXiv cs.RO发布时间待核实
arXiv:2603.15857v2 Announce Type: replace-cross Abstract: Behavioral Foundation Models (BFMs) produce agents with the capability to adapt to any unknown reward or task. These methods, however, are only able to produce near-optimal policies for the reward functions that are in the span of some pre-existing state features, making the choice of state features crucial to the expressivity of the BFM.