Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces

Documenti analoghi

• XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning
  di: Palenicek, Daniel, et al.
  Pubblicazione: (2025)
• Relative Information Gain and Gaussian Process Regression
  di: Flynn, Hamish
  Pubblicazione: (2025)
• Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
  di: Scherer, Christian, et al.
  Pubblicazione: (2026)
• XQCfD: Accelerating Fast Actor-Critic Algorithms with Prior Data and Prior Policies
  di: Palenicek, Daniel, et al.
  Pubblicazione: (2026)
• Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures
  di: Flynn, Hamish, et al.
  Pubblicazione: (2023)