Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization

• URL: http://arxiv.org/abs/2412.18279v1
• Date: Tue, 24 Dec 2024 08:39:35 GMT
• Title: Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization
• Authors: Jiacai Liu, Chaojie Wang, Chris Yuhao Liu, Liang Zeng, Rui Yan, Yiwen Sun, Yang Liu, Yahui Zhou,
• Abstract summary: We introduce Direct Advantage Policy Optimization (DAPO), a novel step-level offline reinforcement learning algorithm. DAPO employs a critic function to predict the reasoning accuracy at each step, thereby generating dense signals to refine the generation strategy. Our results show that DAPO can effectively enhance the mathematical and code capabilities on both SFT models and RL models, demonstrating the effectiveness of DAPO.
• Score: 22.67700436936984
• License:
• Abstract: The role of reinforcement learning (RL) in enhancing the reasoning of large language models (LLMs) is becoming increasingly significant. Despite the success of RL in many scenarios, there are still many challenges in improving the reasoning of LLMs. One challenge is the sparse reward, which makes optimization difficult for RL and necessitates a large amount of data samples. Another challenge stems from the inherent instability of RL, particularly when using Actor-Critic (AC) methods to derive optimal policies, which often leads to unstable training processes. To address these issues, we introduce Direct Advantage Policy Optimization (DAPO), an novel step-level offline RL algorithm. Unlike standard alignment that rely solely outcome rewards to optimize policies (such as DPO), DAPO employs a critic function to predict the reasoning accuracy at each step, thereby generating dense signals to refine the generation strategy. Additionally, the Actor and Critic components in DAPO are trained independently, avoiding the co-training instability observed in standard AC algorithms like PPO. We train DAPO on mathematical and code query datasets and then evaluate its performance on multiple benchmarks. Our results show that DAPO can effectively enhance the mathematical and code capabilities on both SFT models and RL models, demonstrating the effectiveness of DAPO.

Related papers

• Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone [72.17534881026995]
  We develop an offline and online fine-tuning approach called policy-agnostic RL (PA-RL) We show the first result that successfully fine-tunes OpenVLA, a 7B generalist robot policy, autonomously with Cal-QL, an online RL fine-tuning algorithm.
  arXiv  Detail & Related papers  (2024-12-09T17:28:03Z)
• Guiding Reinforcement Learning Using Uncertainty-Aware Large Language Models [1.2233495442213964]
  Large Language Models (LLMs) offer a promising alternative to mitigate RL sample inefficiency and potentially replace human trainers. We address this limitation by a calibrated guidance system that uses Monte Carlo Dropout to enhance LLM advice reliability. We also develop a novel RL policy shaping method based on dynamic model average entropy to adjust the LLM's influence on RL policies according to guidance uncertainty.
  arXiv  Detail & Related papers  (2024-11-15T22:00:29Z)
• VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment [66.80143024475635]
  We propose VinePPO, a straightforward approach to compute unbiased Monte Carlo-based estimates. We show that VinePPO consistently outperforms PPO and other RL-free baselines across MATH and GSM8K datasets.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy Optimization [1.631115063641726]
  We propose a framework that enhances PPO algorithms by incorporating a diffusion model to generate high-quality virtual trajectories for offline datasets. Our contributions are threefold: we explore the potential of diffusion models in RL, particularly for offline datasets, extend the application of online RL to offline environments, and experimentally validate the performance improvements of PPO with diffusion models.
  arXiv  Detail & Related papers  (2024-09-02T19:10:32Z)
• Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment [58.049113055986375]
  We develop a single stage approach named Alignment with Integrated Human Feedback (AIHF) to train reward models and the policy. The proposed approach admits a suite of efficient algorithms, which can easily reduce to, and leverage, popular alignment algorithms. We demonstrate the efficiency of the proposed solutions with extensive experiments involving alignment problems in LLMs and robotic control problems in MuJoCo.
  arXiv  Detail & Related papers  (2024-06-11T01:20:53Z)
• Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms [50.808123629394245]
  Direct Alignment Algorithms (DDAs) like Direct Preference Optimization have emerged as alternatives to the classical RLHF pipeline. This work formulates and formalizes the reward over-optimization or hacking problem for DAAs and explores its consequences across objectives, training regimes, and model scales.
  arXiv  Detail & Related papers  (2024-06-05T03:41:37Z)
• DPO: Differential reinforcement learning with application to optimal configuration search [3.2857981869020327]
  Reinforcement learning with continuous state and action spaces remains one of the most challenging problems within the field. We propose the first differential RL framework that can handle settings with limited training samples and short-length episodes.
  arXiv  Detail & Related papers  (2024-04-24T03:11:12Z)
• Secrets of RLHF in Large Language Models Part I: PPO [81.01936993929127]
  Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. reinforcement learning with human feedback (RLHF) emerges as the pivotal technological paradigm underpinning this pursuit. In this report, we dissect the framework of RLHF, re-evaluate the inner workings of PPO, and explore how the parts comprising PPO algorithms impact policy agent training.
  arXiv  Detail & Related papers  (2023-07-11T01:55:24Z)
• Jump-Start Reinforcement Learning [68.82380421479675]
  We present a meta algorithm that can use offline data, demonstrations, or a pre-existing policy to initialize an RL policy. In particular, we propose Jump-Start Reinforcement Learning (JSRL), an algorithm that employs two policies to solve tasks. We show via experiments that JSRL is able to significantly outperform existing imitation and reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2022-04-05T17:25:22Z)

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.