Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization 文章

ArXiv CS.CV2026-05-29NEWSen作者: Shufan Li, Konstantinos Kallidromitis, Akash Gokul Yusuke Kato, Kazuki Kozuka, Aditya Grover

Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization · 相关技术