Near-Optimal Second-Order Guarantees for Model-Based Adversarial Imitation Learning

Documenti analoghi

• Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation Learning
  di: Li, Shangzhe, et al.
  Pubblicazione: (2026)
• Imitation from Observations with Trajectory-Level Generative Embeddings
  di: Qu, Yongtao, et al.
  Pubblicazione: (2026)
• Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation
  di: Li, Shangzhe, et al.
  Pubblicazione: (2026)
• Reward-free World Models for Online Imitation Learning
  di: Li, Shangzhe, et al.
  Pubblicazione: (2024)
• Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path
  di: Di, Qiwei, et al.
  Pubblicazione: (2024)