PrT-Flow: Probability-Tractable Flow Matching for Reinforcement Learning
cs.RO, cs.AI
Submitted: 2026-10-13
Updated: 2026-10-13
Code: https://github.com/Sunlight-zero/PrT-Flow
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow Matching
- Density estimation using Real NVP
- GenPO++: Generative Policy Optimization with Jacobian-free Likelihood Ratios
- Reinforcement Learning for Flow-Matching Policies with Density Transport
- Flow Matching for Generative Modeling
- Flow Matching Guide and Code
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Flow Matching Policy Gradients
- FALCON: Few-step Accurate Likelihoods for Continuous Flows
- Proximal Policy Optimization Algorithms
- NFPO: Stabilized Policy Optimization of Normalizing Flow for Robotic Policy Learning
- Improving Exploration in Soft-Actor-Critic with Normalizing Flows Policies
- SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows
- SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling
- Max-Entropy Reinforcement Learning with Flow Matching and A Case Study on LQR
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies