method · first seen 7 Oct 2026
flow-based policy
Reinforcement learning policies parameterized by continuous normalizing or flow models that sample actions via integration.
Mentions per week
PapersCodeDiscussion
Earliest sources
- RFPO: Rectified Flow Policy Optimization for Embodied ControlPapers · 7 Oct 2026 · Ting Huang, Lisiyu Pan, Haoyu Wang, Zeyu Zhang, Siyuan Qian, Yanjun Li, Yandong…
- DEFlow: Deep Equilibrium Flow Maximum-Entropy Reinforcement LearningPapers · 12 Oct 2026 · Ruslan Ageev, Huaze Tang, Runqing Miao, Jiarong Li, Wenbo Ding
Latest sources
- DEFlow: Deep Equilibrium Flow Maximum-Entropy Reinforcement LearningPapers · 12 Oct 2026 · Ruslan Ageev, Huaze Tang, Runqing Miao, Jiarong Li, Wenbo Ding
- RFPO: Rectified Flow Policy Optimization for Embodied ControlPapers · 7 Oct 2026 · Ting Huang, Lisiyu Pan, Haoyu Wang, Zeyu Zhang, Siyuan Qian, Yanjun Li, Yandong…