Averaging $n$-step Returns Reduces Variance in Reinforcement Learning

Documenti analoghi

• Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning
  di: Daley, Brett, et al.
  Pubblicazione: (2023)
• Demystifying the Recency Heuristic in Temporal-Difference Learning
  di: Daley, Brett, et al.
  Pubblicazione: (2024)
• An Analysis of Action-Value Temporal-Difference Methods That Learn State Values
  di: Daley, Brett, et al.
  Pubblicazione: (2025)
• Deep Reinforcement Learning with Gradient Eligibility Traces
  di: Elelimy, Esraa, et al.
  Pubblicazione: (2025)
• Harnessing Discrete Representations For Continual Reinforcement Learning
  di: Meyer, Edan, et al.
  Pubblicazione: (2023)