Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference

Similar Items

• Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis
  by: Zhang, Qining, et al.
  Published: (2024)
• Efficient Federated RLHF via Zeroth-Order Policy Optimization
  by: Wang, Deyi, et al.
  Published: (2026)
• Provable Reinforcement Learning from Human Feedback with an Unknown Link Function
  by: Zhang, Qining, et al.
  Published: (2025)
• Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms
  by: Zhang, Qining, et al.
  Published: (2023)
• Gradient Regularization Prevents Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards
  by: Ackermann, Johannes, et al.
  Published: (2026)