Bayesian Flow Networks for Offline Trajectory Planning

2026-08-25

AI Summary

本文提出BFN-RL，基于贝叶斯流网络的离线强化学习框架，通过迭代更新分布参数来处理离散和连续轨迹规划问题。

Abstract

Offline reinforcement learning (RL) leverages static datasets to learn decision policies without real-time environment interaction. While recent sequence-modeling approaches rely on continuous diffusion models for trajectory synthesis, applying these methods to discrete planning tasks requires a categorical formulation rather than the standard Gaussian construction. We present BFN-RL, a unified generative modeling framework for offline RL based on Bayesian Flow Networks (BFNs). By iteratively evolving distribution parameters rather than noisy data instances, BFN-RL natively models both discrete and continuous trajectory spaces within a single probabilistic formulation. The categorical planner generates future state sequences, and a learned inverse-dynamics model converts consecutive generated states into actions. Evaluations in discrete planning and continuous control show that BFN-RL can generate effective trajectories across both categorical and continuous state spaces. Our results establish BFNs as a versatile generative foundation for offline trajectory planning across data modalities.

Problem

• Offline Reinforcement Learning
• Trajectory Synthesis
• Discrete Planning Tasks

Innovation

• Bayesian Flow Networks
• offline reinforcement learning
• discrete and continuous trajectory spaces
• categorical planner
• inverse-dynamics model