Representation Convergence: Mutual Distillation is Secretly a Form of Regularization

Documenti analoghi

• Simple Policy Optimization
  di: Xie, Zhengpeng, et al.
  Pubblicazione: (2024)
• A Dual-Agent Adversarial Framework for Robust Generalization in Deep Reinforcement Learning
  di: Xie, Zhengpeng, et al.
  Pubblicazione: (2025)
• MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy
  di: Wang, Jiaxu, et al.
  Pubblicazione: (2026)
• MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Experts
  di: Xie, Zhitian, et al.
  Pubblicazione: (2024)
• Mutual Information Regularized Offline Reinforcement Learning
  di: Ma, Xiao, et al.
  Pubblicazione: (2022)