REINFORCE++: An Efficient RLHF Algorithm with Robustness to Both Prompt and Reward Models

• URL: http://arxiv.org/abs/2501.03262v3
• Date: Sun, 06 Apr 2025 02:23:29 GMT
• Title: REINFORCE++: An Efficient RLHF Algorithm with Robustness to Both Prompt and Reward Models
• Authors: Jian Hu, Jason Klein Liu, Wei Shen,
• Abstract summary: REINFORCE++ is a novel approach that removes the critic model while using the normalized reward of a batch as the baseline.<n>It exhibits robust performance across various reward models without requiring prompt set truncation.<n>It achieves superior generalization in both RLHF and long chain-of-thought settings compared to existing REINFORCE-based methods.
• Score: 8.587685197004097
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning from Human Feedback (RLHF) plays a crucial role in aligning large language models (LLMs) with human values and preferences. While state-of-the-art applications like ChatGPT/GPT-4 commonly employ Proximal Policy Optimization (PPO), the inclusion of a critic network introduces significant computational overhead. REINFORCE-based methods, such as REINFORCE Leave One-Out (RLOO), ReMax, and Group Relative Policy Optimization (GRPO), address this limitation by eliminating the critic network. However, these approaches face challenges in accurate advantage estimation. Specifically, they estimate advantages independently for responses to each prompt, which can lead to overfitting on simpler prompts and vulnerability to reward hacking. To address these challenges, we introduce REINFORCE++, a novel approach that removes the critic model while using the normalized reward of a batch as the baseline. Our empirical evaluation demonstrates that REINFORCE++ exhibits robust performance across various reward models without requiring prompt set truncation. Furthermore, it achieves superior generalization in both RLHF and long chain-of-thought (CoT) settings compared to existing REINFORCE-based methods. The implementation is available at https://github.com/OpenRLHF/OpenRLHF.

Related papers

• Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning [3.30671592417223]
  Reinforcement learning from human feedback (RLHF) has emerged as a key technique for aligning the output of large language models with human preferences. Most existing RLHF algorithms use the Bradley-Terry model, which relies on assumptions about human preferences that may not reflect the complexity and variability of real-world judgments. We propose a robust algorithm to enhance the performance of existing approaches under such reward model misspecifications.
  arXiv  Detail & Related papers  (2025-04-03T16:16:35Z)
• 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. It requires joint training of an actor and critic with a pretrained, fixed reward model for guidance. 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)
• Graph-attention-based Casual Discovery with Trust Region-navigated Clipping Policy Optimization [13.75709067982844]
  We propose a trust region-navigated clipping policy optimization method for causal discovery.<n>We also propose a refined graph attention encoder called SDGAT to boost the efficient encoding of variables.<n>With these improvements, the proposed method outperforms former RL method in both synthetic and benchmark datasets.
  arXiv  Detail & Related papers  (2024-12-27T10:50:43Z)
• Accelerated Preference Optimization for Large Language Model Alignment [60.22606527763201]
  Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal tool for aligning large language models (LLMs) with human preferences. Direct Preference Optimization (DPO) formulates RLHF as a policy optimization problem without explicitly estimating the reward function. We propose a general Accelerated Preference Optimization (APO) framework, which unifies many existing preference optimization algorithms.
  arXiv  Detail & Related papers  (2024-10-08T18:51:01Z)
• The Perfect Blend: Redefining RLHF with Mixture of Judges [68.58426626501883]
  Reinforcement learning from human feedback (RLHF) has become the leading approach for fine-tuning large language models (LLM) Applying RLHF for MTL currently requires careful tuning of the weights for reward model and data combinations. We introduce a novel post-training paradigm which we called Constrained Generative Policy Optimization (CGPO)
  arXiv  Detail & Related papers  (2024-09-30T15:06:53Z)
• 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. 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)
• REBEL: Reinforcement Learning via Regressing Relative Rewards [59.68420022466047]
  We propose REBEL, a minimalist RL algorithm for the era of generative models.<n>In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL.<n>We find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO.
  arXiv  Detail & Related papers  (2024-04-25T17:20:45Z)
• Towards Efficient Exact Optimization of Language Model Alignment [93.39181634597877]
  Direct preference optimization (DPO) was proposed to directly optimize the policy from preference data. We show that DPO derived based on the optimal solution of problem leads to a compromised mean-seeking approximation of the optimal solution in practice. We propose efficient exact optimization (EXO) of the alignment objective.
  arXiv  Detail & Related papers  (2024-02-01T18:51:54Z)
• Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble [67.4269821365504]
  Reinforcement Learning from Human Feedback (RLHF) is a widely adopted approach for aligning large language models with human values. However, RLHF relies on a reward model that is trained with a limited amount of human preference data. We contribute a reward ensemble method that allows the reward model to make more accurate predictions.
  arXiv  Detail & Related papers  (2024-01-30T00:17:37Z)
• Preference as Reward, Maximum Preference Optimization with Importance Sampling [3.7040071165219595]
  We propose a simple and intuitive off-policy preference optimization algorithm from an importance sampling view, which we call Maximum Preference Optimization (MPO) MPO achieves the best of both worlds by combining the objectives of RLHF and IPO while being an off-policy algorithm.
  arXiv  Detail & Related papers  (2023-12-27T06:34:54Z)
• REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback [61.54791065013767]
  A misalignment between the reward function and human preferences can lead to catastrophic outcomes in the real world. Recent methods aim to mitigate misalignment by learning reward functions from human preferences. We propose a novel concept of reward regularization within the robotic RLHF framework.
  arXiv  Detail & Related papers  (2023-12-22T04:56:37Z)
• SuperHF: Supervised Iterative Learning from Human Feedback [20.22920163075946]
  We focus on two prevalent methods used to align large language models, Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) We propose a novel approach, Supervised Iterative Learning from Human Feedback (SuperHF), which seeks to leverage the strengths of both methods. Our experimental results show SuperHF exceeds PPO-based RLHF on the training objective, easily and favorably trades off high reward with low reward hacking, improves downstream calibration, and performs the same on our GPT-4 based qualitative evaluation scheme all the while being significantly simpler to implement.
  arXiv  Detail & Related papers  (2023-10-25T16:52:00Z)
• Contrastive Preference Learning: Learning from Human Feedback without RL [71.77024922527642]
  We introduce Contrastive Preference Learning (CPL), an algorithm for learning optimal policies from preferences without learning reward functions. CPL is fully off-policy, uses only a simple contrastive objective, and can be applied to arbitrary MDPs.
  arXiv  Detail & Related papers  (2023-10-20T16:37:56Z)
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model [119.65409513119963]
  We introduce a new parameterization of the reward model in RLHF that enables extraction of the corresponding optimal policy in closed form. The resulting algorithm, which we call Direct Preference Optimization (DPO), is stable, performant, and computationally lightweight. Our experiments show that DPO can fine-tune LMs to align with human preferences as well as or better than existing methods.
  arXiv  Detail & Related papers  (2023-05-29T17:57:46Z)

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.