Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow Policies

Documenti analoghi

• HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization
  di: Li, Zeyang, et al.
  Pubblicazione: (2025)
• ECO: Energy-Constrained Operator Learning for Chaotic Dynamics with Boundedness Guarantees
  di: Goertzen, Andrea, et al.
  Pubblicazione: (2025)
• Safe Multi-Agent Reinforcement Learning with Convergence to Generalized Nash Equilibrium
  di: Li, Zeyang, et al.
  Pubblicazione: (2024)
• Learning Dissipative Chaotic Dynamics with Boundedness Guarantees
  di: Tang, Sunbochen, et al.
  Pubblicazione: (2024)
• Meta-Learning for Adaptive Control with Automated Mirror Descent
  di: Tang, Sunbochen, et al.
  Pubblicazione: (2024)