Optimistic Policy Learning under Pessimistic Adversaries with Regret and Violation Guarantees

Documenti analoghi

• Certifiable Safe RLHF: Fixed-Penalty Constraint Optimization for Safer Language Models
  di: Pandit, Kartik, et al.
  Pubblicazione: (2025)
• Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees
  di: Ganguly, Sourav, et al.
  Pubblicazione: (2025)
• Tail-Risk-Safe Monte Carlo Tree Search under PAC-Level Guarantees
  di: Zhang, Zuyuan, et al.
  Pubblicazione: (2025)
• Optimistic Regret Bounds for Online Learning in Adversarial Markov Decision Processes
  di: Moon, Sang Bin, et al.
  Pubblicazione: (2024)
• Provably Efficient Sample Complexity for Robust CMDP
  di: Ganguly, Sourav, et al.
  Pubblicazione: (2025)