近期论文4
- Provably Efficient Online RLHF with One-Pass Reward Modeling第 1 位,共 4 位作者NeurIPS 2025 · 8 次引用
- Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs第 1 位,共 3 位作者NeurIPS 2024 · 5 次引用
- Dynamic Regret of Adversarial MDPs with Unknown Transition and Linear Function Approximation第 1 位,共 3 位作者AAAI 2024 · 3 次引用
- Dynamic Regret of Adversarial Linear Mixture MDPs第 1 位,共 3 位作者NeurIPS 2023 · 7 次引用
