{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Daily Paper Cast","title":"Lean and Mean: Decoupled Value Policy Optimization with Global Value Guidance","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/ea9fcf65\"></iframe>","width":"100%","height":180,"duration":1290,"description":"\n            🤗 Upvotes: 9 | cs.LG, cs.AI\n\n            Authors:\n            Chenghua Huang, Lu Wang, Fangkai Yang, Pu Zhao, Zhixu Li, Qingwei Lin, Dongmei Zhang, Saravan Rajmohan, Qi Zhang\n\n            Title:\n            Lean and Mean: Decoupled Value Policy Optimization with Global Value Guidance\n\n            Arxiv:\n            http://arxiv.org/abs/2502.16944v1\n\n            Abstract:\n            Proximal Policy Optimization (PPO)-based Reinforcement Learning from Human Feedback (RLHF) is essential for aligning large language models (LLMs) with human preferences. It requires joint training of an actor and critic with a pretrained, fixed reward model for guidance. This approach increases computational complexity and instability due to actor-critic interdependence. Additionally, PPO lacks access to true environment rewards in LLM tasks, limiting its adaptability. Under such conditions, pretraining a value model or a reward model becomes equivalent, as both provide fixed supervisory signals without new ground-truth feedback. To address these issues, we propose \\textbf{Decoupled Value Policy Optimization (DVPO)}, a lean framework that replaces traditional reward modeling with a pretrained \\emph{global value model (GVM)}. The GVM is conditioned on policy trajectories and predicts token-level return-to-go estimates. By decoupling value model from policy training (via frozen GVM-driven RL objectives), DVPO eliminates actor-critic interdependence, reducing GPU memory usage by 40\\% and training time by 35\\% compared to conventional RLHF. Experiments across benchmarks show DVPO outperforms efficient RLHF methods (e.g., DPO) while matching state-of-the-art PPO in performance.\n            ","thumbnail_url":"https://img.transistorcdn.com/8lOVNnuwhrA3rxrDMv7Osu4j_t1-jORooO6NfGcQhcw/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81Zjg1/YzRhODczMDU4MmE4/OGMwN2FiNDlmYzI2/MDliMi5qcGVn.webp","thumbnail_width":300,"thumbnail_height":300}