Pessimistic Causal Reinforcement Learning with Mediators for Confounded Offline Data

Documenti analoghi

• Robust Offline Reinforcement learning with Heavy-Tailed Rewards
  di: Zhu, Jin, et al.
  Pubblicazione: (2023)
• Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning
  di: Bai, Chenjia, et al.
  Pubblicazione: (2024)
• Diverse Randomized Value Functions: A Provably Pessimistic Approach for Offline Reinforcement Learning
  di: Yu, Xudong, et al.
  Pubblicazione: (2024)
• Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal Interferences
  di: Dai, Runpeng, et al.
  Pubblicazione: (2024)
• Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning
  di: Luo, Kang, et al.
  Pubblicazione: (2024)