STARC: A General Framework For Quantifying Differences Between Reward Functions

Documenti analoghi

• On the Limitations of Markovian Rewards to Express Multi-Objective, Risk-Sensitive, and Modal Tasks
  di: Skalse, Joar, et al.
  Pubblicazione: (2024)
• Partial Identifiability and Misspecification in Inverse Reinforcement Learning
  di: Skalse, Joar, et al.
  Pubblicazione: (2024)
• Partial Identifiability in Inverse Reinforcement Learning For Agents With Non-Exponential Discounting
  di: Skalse, Joar, et al.
  Pubblicazione: (2024)
• Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification
  di: Skalse, Joar, et al.
  Pubblicazione: (2024)
• The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
  di: Fluri, Lukas, et al.
  Pubblicazione: (2024)