Pre-Trained Policy Discriminators are General Reward Models

• URL: http://arxiv.org/abs/2507.05197v1
• Date: Mon, 07 Jul 2025 16:56:31 GMT
• Title: Pre-Trained Policy Discriminators are General Reward Models
• Authors: Shihan Dou, Shichun Liu, Yuming Yang, Yicheng Zou, Yunhua Zhou, Shuhao Xing, Chenhao Huang, Qiming Ge, Demin Song, Haijun Lv, Songyang Gao, Chengqi Lv, Enyu Zhou, Honglin Guo, Zhiheng Xi, Wenwei Zhang, Qipeng Guo, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Tao Gui, Kai Chen,
• Abstract summary: We propose a scalable pre-training method named Policy Discriminative Learning (POLAR)<n>POLAR trains a reward model (RM) to discern identical policies and discriminate different ones.<n> Empirical results show that POLAR substantially outperforms traditional non-pre-trained methods.
• Score: 81.3974586561645
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We offer a novel perspective on reward modeling by formulating it as a policy discriminator, which quantifies the difference between two policies to generate a reward signal, guiding the training policy towards a target policy with desired behaviors. Based on this conceptual insight, we propose a scalable pre-training method named Policy Discriminative Learning (POLAR), which trains a reward model (RM) to discern identical policies and discriminate different ones. Unlike traditional reward modeling methods relying on absolute preferences, POLAR captures the relative difference between one policy and an arbitrary target policy, which is a scalable, high-level optimization objective suitable for modeling generic ranking relationships. Leveraging the POLAR pre-training paradigm, we present a series of RMs with parameter scales from 1.8B to 7B. Empirical results show that POLAR substantially outperforms traditional non-pre-trained methods, significantly enhancing RM performance. For instance, POLAR-7B could improve preference accuracy from 54.8% to 81.0% on STEM tasks and from 57.9% to 85.5% on creative writing tasks compared to SOTA baselines. POLAR also shows robust generalization capabilities in RLHF using Reinforcement Fine-tuning (RFT), providing reliable reward signals and markedly enhancing policy performance--improving LLaMa3.1-8B from an average of 47.36% to 56.33% and Qwen2.5-32B from 64.49% to 70.47% on 20 benchmarks. Moreover, scaling experiments reveal a clear power-law relationship between computation and performance, supported by linear correlation coefficients approaching 0.99. The impressive performance, strong generalization, and scaling properties suggest that POLAR is a promising direction for developing general and strong reward models.

Related papers

• URPO: A Unified Reward & Policy Optimization Framework for Large Language Models [10.511836918064724]
  We propose a novel framework that unifies instruction-following ("player") and reward modeling ("referee") within a single model and a single training phase.<n>Our method recasts all alignment data-including preference pairs, verifiable reasoning, and open-ended instructions-into a unified generative format.<n>Experiments on the Qwen2.5-7B model demonstrate URPO's superiority.
  arXiv  Detail & Related papers  (2025-07-23T13:52:27Z)
• Value-Free Policy Optimization via Reward Partitioning [0.08192907805418585]
  We introduce Reward Partitioning Optimization (RPO), a new method for single-trajectory reinforcement learning.<n>RPO normalizes observed rewards using a approach estimated directly from data.<n>We validate RPO on scalar-feedback language modeling tasks using Flan-T5 encoder-decoder models.
  arXiv  Detail & Related papers  (2025-06-16T17:06:27Z)
• Lean and Mean: Decoupled Value Policy Optimization with Global Value Guidance [52.65461207786633]
  Policy-based Reinforcement Learning from Human Feedback is essential for aligning large language models with human preferences.<n>It requires joint training of an actor and critic with a pretrained, fixed reward model for guidance.<n>We propose textbfDecoupled Value Policy Optimization (DVPO), a lean framework that replaces traditional reward modeling with a pretrained emphglobal value model (GVM)
  arXiv  Detail & Related papers  (2025-02-24T08:11:33Z)
• Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference [15.038210624870656]
  Reward inference is a critical intermediate step in the Reinforcement Learning from Human Feedback pipeline.<n>This paper develops two RLHF algorithms without reward inference for general RL problems beyond bandits and deterministic MDP bandit, and general preference models beyond the Bradley-Terry model.
  arXiv  Detail & Related papers  (2024-09-25T22:20:11Z)
• Policy Filtration for RLHF to Mitigate Noise in Reward Models [27.278933096153974]
  Policy filtering for Proximal Policy Optimization (PF-PPO)<n>PF-PPO improves the signal-to-noise ratio during policy learning.<n>We provide experiments to validate the effectiveness of PF-PPO in code generation and math reasoning tasks.
  arXiv  Detail & Related papers  (2024-09-11T02:40:38Z)
• Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization [75.1240295759264]
  We propose an effective framework for Bridging and Modeling Correlations in pairwise data, named BMC.<n>We increase the consistency and informativeness of the pairwise preference signals through targeted modifications.<n>We identify that DPO alone is insufficient to model these correlations and capture nuanced variations.
  arXiv  Detail & Related papers  (2024-08-14T11:29:47Z)
• Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning [55.65738319966385]
  We propose a novel online algorithm, iterative Nash policy optimization (INPO)<n>Unlike previous methods, INPO bypasses the need for estimating the expected win rate for individual responses.<n>With an LLaMA-3-8B-based SFT model, INPO achieves a 42.6% length-controlled win rate on AlpacaEval 2.0 and a 37.8% win rate on Arena-Hard.
  arXiv  Detail & Related papers  (2024-06-30T08:00:34Z)
• Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion [43.77763433288893]
  We introduce Contrastive Policy Gradient, or CoPG, a simple and mathematically principled new RL algorithm that can estimate the optimal policy even from off-policy data.<n>We show this approach to generalize the direct alignment method IPO (identity preference optimization) and classic policy gradient.<n>We experiment with the proposed CoPG on a toy bandit problem to illustrate its properties, as well as for finetuning LLMs on a summarization task.
  arXiv  Detail & Related papers  (2024-06-27T14:03:49Z)
• Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning [19.533619091287676]
  We propose a novel preferred-action-optimized diffusion policy for offline reinforcement learning. In particular, an expressive conditional diffusion model is utilized to represent the diverse distribution of a behavior policy. Experiments demonstrate that the proposed method provides competitive or superior performance compared to previous state-of-the-art offline RL methods.
  arXiv  Detail & Related papers  (2024-05-29T03:19:59Z)
• D2PO: Discriminator-Guided DPO with Response Evaluation Models [63.71853401569461]
  We propose D2PO, discriminator-guided DPO, for the online setting where preferences are being collected throughout learning. As we collect gold preferences, we use these not only to train our policy, but to train a discriminative response evaluation model to silver-label even more synthetic data for policy training. We show conditions under which silver labeling is most helpful: it is most effective when training the policy with DPO, outperforming traditional PPO, and benefits from maintaining a separate discriminator from the policy model.
  arXiv  Detail & Related papers  (2024-05-02T17:44:41Z)
• Self-Play Preference Optimization for Language Model Alignment [75.83359213697854]
  Recent advancements suggest that directly working with preference probabilities can yield a more accurate reflection of human preferences. We propose a self-play-based method for language model alignment, which treats the problem as a constant-sum two-player game. Our approach, dubbed Self-Play Preference Optimization (SPPO), utilizes iterative policy updates to provably approximate the Nash equilibrium.
  arXiv  Detail & Related papers  (2024-05-01T17:59:20Z)
• WARM: On the Benefits of Weight Averaged Reward Models [63.08179139233774]
  We propose Weight Averaged Reward Models (WARM) to mitigate reward hacking. Experiments on summarization tasks, using best-of-N and RL methods, shows that WARM improves the overall quality and alignment of LLM predictions.
  arXiv  Detail & Related papers  (2024-01-22T18:27:08Z)
• Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning [53.97273491846883]
  We propose DPE: an RL algorithm that blends offline sequence modeling and offline reinforcement learning with Double Policy Estimation. We validate our method in multiple tasks of OpenAI Gym with D4RL benchmarks.
  arXiv  Detail & Related papers  (2023-08-28T20:46:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.