1
One-Step Bellman Alignment Enables Provably Efficient Transfer in Online RL
提出一步贝尔曼对齐方法，理论上证明能实现高效的在线强化学习迁移。
arXiv:2601.21924v2 Announce Type: replace Abstract: We study online transfer reinforcement learning (RL) in episodic Markov decision processes, where …