Dissecting Deep RL with High Update Ratios: Combatting Value Divergence

Documenti analoghi

• MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL
  di: Voelcker, Claas A, et al.
  Pubblicazione: (2024)
• $λ$-models: Effective Decision-Aware Reinforcement Learning with Latent Models
  di: Voelcker, Claas A, et al.
  Pubblicazione: (2023)
• When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning
  di: Voelcker, Claas, et al.
  Pubblicazione: (2024)
• Relative Entropy Pathwise Policy Optimization
  di: Voelcker, Claas, et al.
  Pubblicazione: (2025)
• Behavior-Consistent Deep Reinforcement Learning
  di: Hussing, Marcel, et al.
  Pubblicazione: (2026)