1
Why Goal-Conditioned Reinforcement Learning Works: Relation to Dual Control
从最优控制视角揭示目标条件强化学习为何有效，推导经典二次型目标与目标奖励之间的最优性差距，为算法设计提供理论支撑。
arXiv:2512.06471v2 Announce Type: replace-cross Abstract: Goal-conditioned reinforcement learning (RL) concerns the problem of training an agent to ma…