1
D2 Actor Critic: Diffusion Actor Meets Distributional Critic
融合扩散模型与分布评论家的新型Actor-Critic算法，在强化学习中实现更稳定高效的策略学习，已被TMLR收录。
arXiv:2510.03508v3 Announce Type: replace Abstract: We introduce D2AC, a new model-free reinforcement learning (RL) algorithm designed to train expres…