Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions
Aligning large language models with pointwise absolute rewards has so far required online, on-policy algorithms such as PPO and GRPO. In contrast, simpler methods that can leverage offline or off-policy data, such as DPO and REBEL, are limited to learning from preference pairs or relative signals. To bridge this gap, we introduce Quantile Reward Policy Optimization (QRPO), which learns from pointwise absolute rewards while preserving the simplicity and offline applicability of DPO-like methods. QRPO uses quantile rewards to enable regression to the closed-form solution of the KL-regularized RL objective. This reward yields an analytically tractable partition function, removing the need for relative signals to cancel this term. Moreover, QRPO scales with increased compute to estimate quantile rewards, opening a new dimension for pre-computation scaling. Empirically, QRPO consistently achieves top performance on chat and coding evaluations--reward model scores, AlpacaEval 2, and LeetCode--compared to DPO, REBEL, and SimPO across diverse datasets and 8B-scale models. Finally, we find that training with robust rewards instead of converting them to preferences induces less length bias.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Quantile-Based Policy Optimization for Reinforcement Learning
Classical reinforcement learning (RL) aims to optimize the expected cumulative rewards. In this work, we consider the RL setting where the goal is to optimize the quantile of the cumulative rewards. We parameterize the p…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Quantile-Based Deep Reinforcement Learning using Two-Timescale Policy Gradient Algorithms
Classical reinforcement learning (RL) aims to optimize the expected cumulative reward. In this work, we consider the RL setting where the goal is to optimize the quantile of the cumulative reward. We parameterize the pol…
Deep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)Vocal Bursts Valence PredictionDistributionally Robust Listwise Preference Optimization
Existing robust preference optimization for language-model alignment mainly studies pairwise supervision and places robustness at the dataset, prompt, or preference-pair level. We instead study listwise preference optimi…
PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling
Reward models (RMs) are central to reinforcement learning from human feedback (RLHF), providing the critical supervision signals that align large language models (LLMs) with human preferences. Generative reward models (G…
Reinforcement LearningPG-Rainbow: Using Distributional Reinforcement Learning in Policy Gradient Methods
This paper introduces PG-Rainbow, a novel algorithm that incorporates a distributional reinforcement learning framework with a policy gradient algorithm. Existing policy gradient methods are sample inefficient and rely o…
Atari GamesDecision MakingDistributional Reinforcement LearningPolicy Gradient Methods+2