作者位次 #3/13ICLR 2026Poster· Reinforcement Learning / Deep RL
RiskPO: Risk-based Policy Optimization with Verifiable Reward for LLM Post-Training
Tao Ren · Jinyang Jiang · Hui Yang · Wan Tian · Minhao Zou · Guanghao Li · Zishi Zhang · Qinghao Wang · Shentao Qin · Yanjun Zhao · Rui Tao · Hui Shao · Yijie Peng
强化学习与后训练OpenReview