SVL: Goal-Conditioned Reinforcement Learning as Survival Learning 事件

SVL: Goal-Conditioned Reinforcement Learning as Survival Learning arXiv:2604.17551v2 Announce Type: replace-cross Abstract: Standard approaches to goal-conditioned reinforcement learning (GCRL) that rely on temporal-difference learning can be unstable and sample-inefficient due to bootstrapping. While recent work has explored contrastive and supervised formulations to improve stability, we present a probabilistic alternative, called survival value learning (SVL), that reframes GCRL as a surviva