Bayesian Flow Networks for Offline Trajectory Planning

arXiv:2608.25163v1 Announce Type: new 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.

Related

• Learning to Plan, Planning to Learn: Adaptive Hierarchical RL-MPC for Sample-Efficient Decision Making
• Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning
• IFlowNets: Extending Generative Samplers to Learn Strategies in Incomplete Information Games
• Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidance
• Stable GFlowNets with Probabilistic Guarantees

Source: arXiv cs.LG | 2026-08-27