Csaba Szepesvári

ORCID：0000-0002-9286-2892

发表论文 444 篇 · 总被引 16838 次 · h-index 56

代表论文

• When Is Partially Observable Reinforcement Learning Not Scary? (2022 · arXiv (Cornell University) · 被引 8)
• Optimistic MLE: A Generic Model-Based Algorithm for Partially Observable Sequential Decision Making (2023 · 被引 7)
• Sample-Efficient Reinforcement Learning of Partially Observable Markov Games (2022 · arXiv (Cornell University) · 被引 7)
• Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization (2022 · arXiv (Cornell University) · 被引 4)
• To Believe or Not to Believe Your LLM (2024 · arXiv (Cornell University) · 被引 3)
• Near-Optimal Sample Complexity Bounds for Constrained MDPs (2022 · arXiv (Cornell University) · 被引 3)