Mildly Conservative Q-Learning for Offline Reinforcement Learning

Documenti analoghi

• SEABO: A Simple Search-Based Method for Offline Imitation Learning
  di: Lyu, Jiafei, et al.
  Pubblicazione: (2024)
• Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence
  di: Lyu, Jiafei, et al.
  Pubblicazione: (2024)
• Cross-Domain Policy Adaptation by Capturing Representation Mismatch
  di: Lyu, Jiafei, et al.
  Pubblicazione: (2024)
• ODRL: A Benchmark for Off-Dynamics Reinforcement Learning
  di: Lyu, Jiafei, et al.
  Pubblicazione: (2024)
• Mildly Conservative Regularized Evaluation for Offline Reinforcement Learning
  di: Chen, Haohui, et al.
  Pubblicazione: (2025)