paper-with-me

홈 › Papers

Generalisation of RLHF under Reward Shift and Clipped KL Regularisation

2026-02-25 · Kenton Tang, Yuzhu Chen, Fengxiang He arxiv

Alignment and adaptation in large language models heavily rely on reinforcement learning from human feedback (RLHF); yet, theoretical understanding of its generalisability remains premature, especially when the learned reward could shift, and the KL control is estimated and clipped. To address this issue, we develop generalisation theory for RLHF that explicitly accounts for (1) \emph{reward shift}: reward models are trained on preference data from earlier or mixed behaviour policies while RLHF optimises the current policy on its own rollouts; and (2) \emph{clipped KL regularisation}: the KL regulariser is estimated from sampled log-probability ratios and then clipped for stabilisation, resulting in an error to RLHF. We present generalisation bounds for RLHF, suggesting that the generalisation error stems from a sampling error from prompts and rollouts, a reward shift error, and a KL clipping error. We also discuss special cases of (1) initialising RLHF parameters with a uniform prior over a finite space, and (2) training RLHF by stochastic gradient descent, as an Ornstein-Uhlenbeck process. The theory yields practical implications in (1) optimal KL clipping threshold, and (2) budget allocation in prompts, rollouts, and preference data.

📄 PDF Abstract BibTeX arXiv:2602.21765

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Understanding the Effects of RLHF on LLM Generalisation and Diversity

2023-10-10 · Robert Kirk, Ishita Mediratta, Christoforos Nalmpantis, Jelena Luketina 외

Large language models (LLMs) fine-tuned with reinforcement learning from human feedback (RLHF) have been used in some of the most widely deployed AI models to date, such as OpenAI's ChatGPT or Anthropic's Claude. While t…

DiversityInstruction Following

Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF

2026-06-25 · Arnav Raj arxiv

Reinforcement learning from human feedback (RLHF) in production does not always have a synchronous reward signal. Code-execution verifiers, slow judge ensembles, and queued human review can return several gradient steps …

Reinforcement Learning

Towards Efficient Online Exploration for Reinforcement Learning with Human Feedback

2025-09-26 · Gen Li, Yuling Yan arxiv

Reinforcement learning with human feedback (RLHF), which learns a reward model from human preference data and then optimizes a policy to favor preferred responses, has emerged as a central paradigm for aligning large lan…

Reinforcement Learning

REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback

2023-12-22 · Souradip Chakraborty, Anukriti Singh, Amisha Bhaskar, Pratap Tokekar 외

The effectiveness of reinforcement learning (RL) agents in continuous control robotics tasks is mainly dependent on the design of the underlying reward function, which is highly prone to reward hacking. A misalignment be…

Bilevel Optimizationcontinuous-controlContinuous Controlreinforcement-learning+1

Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis

2024-06-11 · Qining Zhang, Honghao Wei, Lei Ying

In this paper, we study reinforcement learning from human feedback (RLHF) under an episodic Markov decision process with a general trajectory-wise reward model. We developed a model-free RLHF best policy identification a…