SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning

Documenti analoghi

• A Benchmark Environment for Offline Reinforcement Learning in Racing Games
  di: Macaluso, Girolamo, et al.
  Pubblicazione: (2024)
• SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data
  di: Romeo, Carlo, et al.
  Pubblicazione: (2026)
• Offline Reinforcement Learning with Imputed Rewards
  di: Romeo, Carlo, et al.
  Pubblicazione: (2024)
• TROFI: Trajectory-Ranked Offline Inverse Reinforcement Learning
  di: Sestini, Alessandro, et al.
  Pubblicazione: (2025)
• ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders
  di: Romeo, Carlo, et al.
  Pubblicazione: (2026)