Prior-Guided Diffusion Planning for Offline Reinforcement Learning

• URL: http://arxiv.org/abs/2505.10881v1
• Date: Fri, 16 May 2025 05:39:02 GMT
• Title: Prior-Guided Diffusion Planning for Offline Reinforcement Learning
• Authors: Donghyeon Ki, JunHyeok Oh, Seong-Woong Shim, Byung-Jun Lee,
• Abstract summary: Prior Guidance (PG) is a novel guided sampling framework that replaces the standard Gaussian prior-of-cloned diffusion model.<n>PG directly generates high-value trajectories without costly reward optimization of the diffusion model itself.<n>We present an efficient training strategy that applies behavior regularization in latent space, and empirically demonstrate that PG outperforms state-the-art diffusion policies and planners across diverse long-horizon offline RL benchmarks.
• Score: 4.760537994346813
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models have recently gained prominence in offline reinforcement learning due to their ability to effectively learn high-performing, generalizable policies from static datasets. Diffusion-based planners facilitate long-horizon decision-making by generating high-quality trajectories through iterative denoising, guided by return-maximizing objectives. However, existing guided sampling strategies such as Classifier Guidance, Classifier-Free Guidance, and Monte Carlo Sample Selection either produce suboptimal multi-modal actions, struggle with distributional drift, or incur prohibitive inference-time costs. To address these challenges, we propose Prior Guidance (PG), a novel guided sampling framework that replaces the standard Gaussian prior of a behavior-cloned diffusion model with a learnable distribution, optimized via a behavior-regularized objective. PG directly generates high-value trajectories without costly reward optimization of the diffusion model itself, and eliminates the need to sample multiple candidates at inference for sample selection. We present an efficient training strategy that applies behavior regularization in latent space, and empirically demonstrate that PG outperforms state-of-the-art diffusion policies and planners across diverse long-horizon offline RL benchmarks.

Related papers

• Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning [0.0]
  We propose a generative policy trained with an augmented flow-matching objective to predict direct completion vectors from intermediate flow samples.<n>Our method scales effectively to offline, offline-to-online, and online RL settings, offering substantial gains in speed and adaptability.<n>We extend SSCP to goal-conditioned RL, enabling flat policies to exploit subgoal structures without explicit hierarchical inference.
  arXiv  Detail & Related papers  (2025-06-26T16:09:53Z)
• VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL [28.95582264086289]
  VAlue-based Reinforced Diffusion (VARD) is a novel approach that first learns a value function predicting expection of rewards from intermediate states.<n>Our method maintains proximity to the pretrained model while enabling effective and stable training via backpropagation.
  arXiv  Detail & Related papers  (2025-05-21T17:44:37Z)
• Model-Based Offline Reinforcement Learning with Adversarial Data Augmentation [36.9134885948595]
  We introduce Model-based Offline Reinforcement learning with AdversariaL data augmentation.<n>In MORAL, we replace the fixed horizon rollout by employing adversaria data augmentation to execute alternating sampling with ensemble models.<n>Experiments on D4RL benchmark demonstrate that MORAL outperforms other model-based offline RL methods in terms of policy learning and sample efficiency.
  arXiv  Detail & Related papers  (2025-03-26T07:24:34Z)
• DPR: Diffusion Preference-based Reward for Offline Reinforcement Learning [30.654668373387214]
  We propose a novel preference-based reward acquisition method: Diffusion Preference-based Reward (DPR)<n>DPR uses diffusion models to directly model preference distributions for state-action pairs, allowing rewards to be discriminatively obtained from these distributions.<n>We apply the above methods to existing offline reinforcement learning algorithms and a series of experiment results demonstrate that the diffusion-based reward acquisition approach outperforms previous-based and Transformer-based methods.
  arXiv  Detail & Related papers  (2025-03-03T03:49:38Z)
• Test-time Alignment of Diffusion Models without Reward Over-optimization [8.981605934618349]
  Diffusion models excel in generative tasks, but aligning them with specific objectives remains challenging.<n>We propose a training-free, test-time method based on Sequential Monte Carlo (SMC) to sample from the reward-aligned target distribution.<n>We demonstrate its effectiveness in single-reward optimization, multi-objective scenarios, and online black-box optimization.
  arXiv  Detail & Related papers  (2025-01-10T09:10:30Z)
• Prompt Tuning with Diffusion for Few-Shot Pre-trained Policy Generalization [55.14484317645865]
  We develop a conditional diffusion model to produce exceptional quality prompts for offline reinforcement learning tasks. We show that the Prompt diffuser is a robust and effective tool for the prompt-tuning process, demonstrating strong performance in the meta-RL tasks.
  arXiv  Detail & Related papers  (2024-11-02T07:38:02Z)
• Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization [165.98557106089777]
  A key challenge is to enhance the capabilities of large language models (LLMs) amid a looming shortage of high-quality training data. Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets. We then formalize this strategy into a principled framework of Instance-Reweighted Distributionally Robust Optimization.
  arXiv  Detail & Related papers  (2024-02-22T04:10:57Z)
• Manifold Preserving Guided Diffusion [121.97907811212123]
  Conditional image generation still faces challenges of cost, generalizability, and the need for task-specific training. We propose Manifold Preserving Guided Diffusion (MPGD), a training-free conditional generation framework.
  arXiv  Detail & Related papers  (2023-11-28T02:08:06Z)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning [70.20191211010847]
  Offline reinforcement learning (RL) aims to learn an optimal policy using a previously collected static dataset. We introduce Diffusion Q-learning (Diffusion-QL) that utilizes a conditional diffusion model to represent the policy. We show that our method can achieve state-of-the-art performance on the majority of the D4RL benchmark tasks.
  arXiv  Detail & Related papers  (2022-08-12T09:54:11Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)

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.