A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees

Documenti analoghi

• Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
  di: Kitamura, Toshinori, et al.
  Pubblicazione: (2025)
• Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying
  di: Nishimori, Soichiro, et al.
  Pubblicazione: (2026)
• Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form
  di: Kitamura, Toshinori, et al.
  Pubblicazione: (2024)
• Discovering New Theorems via LLMs with In-Context Proof Learning in Lean
  di: Kasaura, Kazumi, et al.
  Pubblicazione: (2025)
• LeanConjecturer: Automatic Generation of Mathematical Conjectures for Theorem Proving
  di: Onda, Naoto, et al.
  Pubblicazione: (2025)