paper-with-me

홈 › Papers

RREDCoT: Segment-Level Reward Redistribution for Reasoning Models

2026-06-04 · Mykyta Ielanskyi, Kajetan Schweighofer, Lukas Aichberger, Sepp Hochreiter arxiv

Recent advancements in reasoning language models have been driven by Reinforcement Learning (RL) fine-tuning. Most often, these rely on the Group Relative Policy Optimization (GRPO) algorithm or modifications thereof to steer the models to produce Chain-of-Thought (CoT) traces. The final answer can only be verified, and the reward assigned, after the CoT trace is complete, making it a delayed reward problem. GRPO and its modifications correspond to Monte Carlo methods in standard RL, which are known to suffer from high variance. A possible solution to this problem is the redistribution of rewards through credit assignment, where segments of the CoT trace that are important for arriving at the desirable solution are emphasized by assigning a higher reward. While Monte Carlo sampling can be used to provide an unbiased estimate of intermediate state values, its computational overhead makes it unsuitable for train-time credit assignment in long contexts at high granularity. We introduce RREDCoT (Reward REDistribution for Chain of Thoughts), which utilizes the model itself to approximate the optimal reward redistribution without additional generation. We investigate the advantages of our method compared to MC sampling and several attribution methods. We further analyze several aspects relevant to the construction of the redistribution such as segmentation of CoT traces and state value estimation.

📄 PDF Abstract BibTeX arXiv:2606.06475

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution

2020-09-29 · Vihang P. Patil, Markus Hofmarcher, Marius-Constantin Dinu, Matthias Dorfer 외

Reinforcement learning algorithms require many samples when solving complex hierarchical tasks with sparse and delayed rewards. For such complex tasks, the recently proposed RUDDER uses reward redistribution to leverage …

General Reinforcement LearningMinecraftMultiple Sequence AlignmentSafe Exploration

Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach

2023-05-28 · NeurIPS 2023 11 · Yudi Zhang, Yali Du, Biwei Huang, Ziyan Wang 외

A major challenge in reinforcement learning is to determine which state-action pairs are responsible for future rewards that are delayed. Reward redistribution serves as a solution to re-assign credits for each time step…

reinforcement-learningReinforcement Learning

Likelihood Reward Redistribution

2025-03-20 · Minheng Xiao, Zhenbang Jiao

In many practical reinforcement learning scenarios, feedback is provided only at the end of a long horizon, leading to sparse and delayed rewards. Existing reward redistribution methods typically assume that per-step rew…

MuJoCo

Towards Long-delayed Sparsity: Learning a Better Transformer through Reward Redistribution

2023-02-01 · journal 2023 2 · Tianchen Zhu, Yue Qiu, Haoyi Zhou, JianXin Li

Recently, Decision Transformer (DT) pioneered theoffine RL into a contextual conditional sequencemodeling paradigm, which leverages self-attendedautoregression to learn from global target rewards,states, and actions. How…

TreeAdv: Tree-Structured Advantage Redistribution for Group-Based RL

2026-01-07 · Lang Cao, Hui Ruan, Yongqian Li, Peng Chao 외 arxiv

Reinforcement learning with group-based objectives, such as Group Relative Policy Optimization (GRPO), is a common framework for aligning large language models on complex reasoning tasks. However, standard GRPO treats ea…

Reinforcement Learning