paper-with-me

홈 › Papers

GOPO: Policy Optimization using Ranked Rewards

2026-02-01 · Kyuseong Choi, Dwaipayan Saha, Woojeong Kim, Anish Agarwal, Raaz Dwivedi arxiv

Standard reinforcement learning from human feedback (RLHF) trains a reward model on pairwise preference data and then uses it for policy optimization. However, while reward models are optimized to capture relative preferences, existing policy optimization techniques rely on absolute reward magnitudes during training. In settings where the rewards are non-verifiable such as summarization, instruction following, and chat completion, this misalignment often leads to suboptimal performance. We introduce Group Ordinal Policy Optimization (GOPO), a policy optimization method that uses only the ranking of the rewards and discards their magnitudes. Our rank-based transformation of rewards provides several gains, compared to Group Relative Policy Optimization (GRPO), in settings with non-verifiable rewards: (1) consistently higher training/validation reward trajectories, (2) improved LLM-as-judge evaluations across most intermediate training steps, and (3) reaching a policy of comparable quality in substantially less training steps than GRPO. We demonstrate consistent improvements across a range of tasks and model sizes.

📄 PDF Abstract BibTeX arXiv:2602.03876

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningInstruction Following

Similar Papers 제목 키워드 기반

Group Orthogonalized Policy Optimization:Group Policy Optimization as Orthogonal Projection in Hilbert Space

2026-02-24 · Wang Zixian arxiv

We present Group Orthogonalized Policy Optimization (GOPO), a new alignment algorithm for large language models derived from the geometry of Hilbert function spaces. Instead of optimizing on the probability simplex and i…

Mathematical Reasoning

Enhanced LLM Reasoning by Optimizing Reward Functions with Search-Driven Reinforcement Learning

2026-05-03 · Arash Ahmadi, Sarah Sharif, Yaser, Banad arxiv

Mathematical reasoning is a key benchmark for large language models. Reinforcement learning is a standard post-training mechanism for improving the reasoning capabilities of large language models, yet performance remains…

Reinforcement LearningMathematical Reasoning

Decoupling Strategy and Execution in Task-Focused Dialogue via Goal-Oriented Preference Optimization

2026-01-24 · Jingyi Xu, Xingyu Ren, Zhoupeng Shou, Yumeng Zhang 외 arxiv

Large language models show potential in task-oriented dialogue systems, yet existing training methods often rely on token-level likelihood or preference optimization, which poorly align with long-horizon task success. To…

Hierarchical Reinforcement LearningTask-Oriented Dialogue SystemsResponse Generation

Regulating Oligopolistic Competition

2023-02-07 · Kai Hao Yang, Alexander K. Zentefis

We consider the problem of how to regulate an oligopoly when firms have private information about their costs. In the environment, consumers make discrete choices over goods, and minimal structure is placed on the manner…

Truncate Bad, Upweight Good: BoN-Style Distillation via Rank-Based Classification

2026-08-20 · Yarin Bar, Yaniv Romano arxiv

Inference-time selection methods, such as Best-of-N, improve generation by sampling a pool of candidates and selecting the top-ranked completion according to a reward model. Distillation seeks to amortize this procedure …