DeFlow: Decoupling Manifold Modeling and Value Maximization for Offline Policy Extraction

Documenti analoghi

• Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning
  di: Mu, Zhancun, et al.
  Pubblicazione: (2026)
• A Contextual Combinatorial Bandit Approach to Negotiation
  di: Li, Yexin, et al.
  Pubblicazione: (2024)
• ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignment
  di: Cai, Shaofei, et al.
  Pubblicazione: (2025)
• Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning
  di: Tiofack, Franki Nguimatsia, et al.
  Pubblicazione: (2025)
• Modular Diffusion Policy Training: Decoupling and Recombining Guidance and Diffusion for Offline RL
  di: Chen, Zhaoyang, et al.
  Pubblicazione: (2025)