Provable Reward-Agnostic Preference-Based Reinforcement Learning

Ähnliche Einträge

• Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond
  von: Chen, Fan, et al.
  Veröffentlicht: (2022)
• Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes
  von: Lu, Miao, et al.
  Veröffentlicht: (2022)
• Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining
  von: Lin, Licong, et al.
  Veröffentlicht: (2023)
• Learning Hierarchical Polynomials of Multiple Nonlinear Features with Three-Layer Networks
  von: Fu, Hengyu, et al.
  Veröffentlicht: (2024)
• On the Provable Performance Guarantee of Efficient Reasoning Models
  von: Zeng, Hao, et al.
  Veröffentlicht: (2025)