Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning

• URL: http://arxiv.org/abs/2504.04524v1
• Date: Sun, 06 Apr 2025 15:48:26 GMT
• Title: Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning
• Authors: Xuerui Su, Shufang Xie, Guoqing Liu, Yingce Xia, Renqian Luo, Peiran Jin, Zhiming Ma, Yue Wang, Zun Wang, Yuting Liu,
• Abstract summary: We propose the Trust Region Preference Approximation (TRPA) algorithm.<n>As a preference-based algorithm, TRPA naturally eliminates the reward hacking issue.<n> Experimental results demonstrate that TRPA not only achieves competitive performance on reasoning tasks but also exhibits robust stability.
• Score: 36.00719049772089
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, Large Language Models (LLMs) have rapidly evolved, approaching Artificial General Intelligence (AGI) while benefiting from large-scale reinforcement learning to enhance Human Alignment (HA) and Reasoning. Recent reward-based optimization algorithms, such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO) have achieved significant performance on reasoning tasks, whereas preference-based optimization algorithms such as Direct Preference Optimization (DPO) significantly improve the performance of LLMs on human alignment. However, despite the strong performance of reward-based optimization methods in alignment tasks , they remain vulnerable to reward hacking. Furthermore, preference-based algorithms (such as Online DPO) haven't yet matched the performance of reward-based optimization algorithms (like PPO) on reasoning tasks, making their exploration in this specific area still a worthwhile pursuit. Motivated by these challenges, we propose the Trust Region Preference Approximation (TRPA) algorithm, which integrates rule-based optimization with preference-based optimization for reasoning tasks. As a preference-based algorithm, TRPA naturally eliminates the reward hacking issue. TRPA constructs preference levels using predefined rules, forms corresponding preference pairs, and leverages a novel optimization algorithm for RL training with a theoretical monotonic improvement guarantee. Experimental results demonstrate that TRPA not only achieves competitive performance on reasoning tasks but also exhibits robust stability. The code of this paper are released and updating on https://github.com/XueruiSu/Trust-Region-Preference-Approximation.git.

Related papers

• 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. We also propose a refined graph attention encoder called SDGAT to boost the efficient encoding of variables. 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)
• Discovering Preference Optimization Algorithms with and for Large Language Models [50.843710797024805]
  offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs. We perform objective discovery to automatically discover new state-of-the-art preference optimization algorithms without (expert) human intervention. Experiments demonstrate the state-of-the-art performance of DiscoPOP, a novel algorithm that adaptively blends logistic and exponential losses.
  arXiv  Detail & Related papers  (2024-06-12T16:58:41Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences.<n>To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.<n>Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)
• Surpassing legacy approaches to PWR core reload optimization with single-objective Reinforcement learning [0.0]
  We have developed methods based on Deep Reinforcement Learning (DRL) for both single- and multi-objective optimization. In this paper, we demonstrate the advantage of our RL-based approach, specifically using Proximal Policy Optimization (PPO) PPO adapts its search capability via a policy with learnable weights, allowing it to function as both a global and local search method.
  arXiv  Detail & Related papers  (2024-02-16T19:35:58Z)
• 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)
• 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)
• Near Optimal Policy Optimization via REPS [33.992374484681704]
  emphrelative entropy policy search (REPS) has demonstrated successful policy learning on a number of simulated and real-world robotic domains. There exist no guarantees on REPS's performance when using gradient-based solvers. We introduce a technique that uses emphgenerative access to the underlying decision process to compute parameter updates that maintain favorable convergence to the optimal regularized policy.
  arXiv  Detail & Related papers  (2021-03-17T16:22:59Z)
• Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO [90.90009491366273]
  We study the roots of algorithmic progress in deep policy gradient algorithms through a case study on two popular algorithms. Specifically, we investigate the consequences of "code-level optimizations:" Our results show that they (a) are responsible for most of PPO's gain in cumulative reward over TRPO, and (b) fundamentally change how RL methods function.
  arXiv  Detail & Related papers  (2020-05-25T16:24:59Z)
• Provably Efficient Exploration in Policy Optimization [117.09887790160406]
  This paper proposes an Optimistic variant of the Proximal Policy Optimization algorithm (OPPO) OPPO achieves $tildeO(sqrtd2 H3 T )$ regret. To the best of our knowledge, OPPO is the first provably efficient policy optimization algorithm that explores.
  arXiv  Detail & Related papers  (2019-12-12T08:40:02Z)

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.