LLM Value Functions for Credit Assignment in Agentic RL
Reinforcement learning (RL) for large language model (LLM) agents remains challenging in long-horizon tasks with sparse outcome rewards, where assigning credit to individual actions is difficult. Methods such as GRPO assign the same trajectory-level advantage to all actions, while critic-based methods require learning...
Kai-Jie Zhu, Wei-Xiang Yan, Omar Attia et al.
· 0 citations