ODRL: A Benchmark for Off-Dynamics Reinforcement Learning

Documenti analoghi

• Cross-Domain Policy Adaptation by Capturing Representation Mismatch
  di: Lyu, Jiafei, et al.
  Pubblicazione: (2024)
• Mildly Conservative Q-Learning for Offline Reinforcement Learning
  di: Lyu, Jiafei, et al.
  Pubblicazione: (2022)
• Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence
  di: Lyu, Jiafei, et al.
  Pubblicazione: (2024)
• PROF: An LLM-based Reward Code Preference Optimization Framework for Offline Imitation Learning
  di: Sun, Shengjie, et al.
  Pubblicazione: (2025)
• SEABO: A Simple Search-Based Method for Offline Imitation Learning
  di: Lyu, Jiafei, et al.
  Pubblicazione: (2024)