#artificial intelligence
Apr 2026
Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning
Low-Rank Adaptation (LoRA) is proposed as a structural regularizer for critic learning from scratch that reduces critic loss during training and improves overall policy performance, achieving the best or competitive results on most tasks.
Yuan Zhuang, Yuexin Bian, Si-Hong He et al.
· arXiv.org · 0 citations