Process Reward Model with Q-Value Rankings

• URL: http://arxiv.org/abs/2410.11287v1
• Date: Tue, 15 Oct 2024 05:10:34 GMT
• Title: Process Reward Model with Q-Value Rankings
• Authors: Wendi Li, Yixuan Li,
• Abstract summary: Process Reward Modeling (PRM) is critical for complex reasoning and decision-making tasks. We introduce the Process Q-value Model (PQM), a novel framework that redefines PRM in the context of a Markov Decision Process. PQM optimize Q-value rankings based on a novel comparative loss function, enhancing the model's ability to capture the intricate dynamics among sequential decisions.
• Score: 18.907163177605607
• License:
• Abstract: Process Reward Modeling (PRM) is critical for complex reasoning and decision-making tasks where the accuracy of intermediate steps significantly influences the overall outcome. Existing PRM approaches, primarily framed as classification problems, employ cross-entropy loss to independently evaluate each step's correctness. This method can lead to suboptimal reward distribution and does not adequately address the interdependencies among steps. To address these limitations, we introduce the Process Q-value Model (PQM), a novel framework that redefines PRM in the context of a Markov Decision Process. PQM optimizes Q-value rankings based on a novel comparative loss function, enhancing the model's ability to capture the intricate dynamics among sequential decisions. This approach provides a more granular and theoretically grounded methodology for process rewards. Our extensive empirical evaluations across various sampling policies, language model backbones, and multi-step reasoning benchmarks show that PQM outperforms classification-based PRMs. The effectiveness of the comparative loss function is highlighted in our comprehensive ablation studies, confirming PQM's practical efficacy and theoretical advantage.

Related papers

• Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization [50.485788083202124]
  Reinforcement Learning (RL) plays a crucial role in aligning large language models with human preferences and improving their ability to perform complex tasks. We introduce Direct Q-function Optimization (DQO), which formulates the response generation process as a Markov Decision Process (MDP) and utilizes the soft actor-critic (SAC) framework to optimize a Q-function directly parameterized by the language model. Experimental results on two math problem-solving datasets, GSM8K and MATH, demonstrate that DQO outperforms previous methods, establishing it as a promising offline reinforcement learning approach for aligning language models.
  arXiv  Detail & Related papers  (2024-10-11T23:29:20Z)
• Prior Constraints-based Reward Model Training for Aligning Large Language Models [58.33118716810208]
  This paper proposes a Prior Constraints-based Reward Model (namely PCRM) training method to mitigate this problem. PCRM incorporates prior constraints, specifically, length ratio and cosine similarity between outputs of each comparison pair, during reward model training to regulate optimization magnitude and control score margins. Experimental results demonstrate that PCRM significantly improves alignment performance by effectively constraining reward score scaling.
  arXiv  Detail & Related papers  (2024-04-01T07:49:11Z)
• Variational Inference of Parameters in Opinion Dynamics Models [9.51311391391997]
  This work uses variational inference to estimate the parameters of an opinion dynamics ABM. We transform the inference process into an optimization problem suitable for automatic differentiation. Our approach estimates both macroscopic (bounded confidence intervals and backfire thresholds) and microscopic ($200$ categorical, agent-level roles) more accurately than simulation-based and MCMC methods.
  arXiv  Detail & Related papers  (2024-03-08T14:45:18Z)
• Let's reward step by step: Step-Level reward model as the Navigators for Reasoning [64.27898739929734]
  Process-Supervised Reward Model (PRM) furnishes LLMs with step-by-step feedback during the training phase. We propose a greedy search algorithm that employs the step-level feedback from PRM to optimize the reasoning pathways explored by LLMs. To explore the versatility of our approach, we develop a novel method to automatically generate step-level reward dataset for coding tasks and observed similar improved performance in the code generation tasks.
  arXiv  Detail & Related papers  (2023-10-16T05:21:50Z)
• Provably Efficient UCB-type Algorithms For Learning Predictive State Representations [55.00359893021461]
  The sequential decision-making problem is statistically learnable if it admits a low-rank structure modeled by predictive state representations (PSRs) This paper proposes the first known UCB-type approach for PSRs, featuring a novel bonus term that upper bounds the total variation distance between the estimated and true models. In contrast to existing approaches for PSRs, our UCB-type algorithms enjoy computational tractability, last-iterate guaranteed near-optimal policy, and guaranteed model accuracy.
  arXiv  Detail & Related papers  (2023-07-01T18:35:21Z)
• Decision-Dependent Distributionally Robust Markov Decision Process Method in Dynamic Epidemic Control [4.644416582073023]
  The Susceptible-Exposed-Infectious-Recovered (SEIR) model is widely used to represent the spread of infectious diseases. We present a Distributionally Robust Markov Decision Process (DRMDP) approach for addressing the dynamic epidemic control problem.
  arXiv  Detail & Related papers  (2023-06-24T20:19:04Z)
• Policy Gradient With Serial Markov Chain Reasoning [10.152838128195468]
  We introduce a new framework that performs decision-making in reinforcement learning as an iterative reasoning process. We show our framework has several useful properties that are inherently missing from traditional RL. Our resulting algorithm achieves state-of-the-art performance in popular Mujoco and DeepMind Control benchmarks.
  arXiv  Detail & Related papers  (2022-10-13T06:15:29Z)
• Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts [52.844741540236285]
  This paper investigates the model-based methods in multi-agent reinforcement learning (MARL) We propose a novel decentralized model-based MARL method, named Adaptive Opponent-wise Rollout Policy (AORPO)
  arXiv  Detail & Related papers  (2021-05-07T16:20:22Z)
• Stein Variational Model Predictive Control [130.60527864489168]
  Decision making under uncertainty is critical to real-world, autonomous systems. Model Predictive Control (MPC) methods have demonstrated favorable performance in practice, but remain limited when dealing with complex distributions. We show that this framework leads to successful planning in challenging, non optimal control problems.
  arXiv  Detail & Related papers  (2020-11-15T22:36:59Z)

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.