TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning

Documenti analoghi

• Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning
  di: Wagenmaker, Andrew, et al.
  Pubblicazione: (2025)
• Residual Off-Policy RL for Finetuning Behavior Cloning Policies
  di: Ankile, Lars, et al.
  Pubblicazione: (2025)
• Steering Your Diffusion Policy with Latent Space Reinforcement Learning
  di: Wagenmaker, Andrew, et al.
  Pubblicazione: (2025)
• Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
  di: Zhu, Chuning, et al.
  Pubblicazione: (2025)
• PEEK: Guiding and Minimal Image Representations for Zero-Shot Generalization of Robot Manipulation Policies
  di: Zhang, Jesse, et al.
  Pubblicazione: (2025)