Profiles2020-2026
Nan Jiang
Siebel School of Computing and Data Science
29Papers
17Last author
49Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers29
- A Unifying View of Coverage in Linear Off-policy EvaluationAuthor 4 of 4ICLR 2026 · 2 citations
- On the Tension Between Optimality and Adversarial Robustness in Policy OptimizationAuthor 8 of 8ICLR 2026
- Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RLAuthor 6 of 7NeurIPS 2025 · 28 citations
- A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement LearningAuthor 6 of 8NeurIPS 2025 · 13 citations
- Model Selection for Off-policy Evaluation: New Algorithms and Experimental ProtocolAuthor 7 of 7NeurIPS 2025 · 6 citations
- Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time AlignmentAuthor 3 of 3ICML 2025
- Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret LearningAuthor 7 of 9ICLR 2025
- Online Iterative Reinforcement Learning from Human Feedback with General Preference ModelAuthor 5 of 6NeurIPS 2024 · 60 citations
- Harnessing Density Ratios for Online Reinforcement LearningAuthor 2 of 2ICLR 2024 · 14 citations
- On the Curses of Future and History in Future-dependent Value Functions for Off-policy EvaluationAuthor 2 of 2NeurIPS 2024 · 11 citations
- Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic ModularityAuthor 2 of 2NeurIPS 2024 · 6 citations
- Occupancy-based Policy Gradient: Estimation, Convergence, and OptimalityAuthor 2 of 2NeurIPS 2024 · 5 citations
- Adversarial Model for Offline Reinforcement LearningAuthor 4 of 5NeurIPS 2023 · 44 citations
- Future-Dependent Value-Based Off-Policy Evaluation in POMDPsAuthor 6 of 9NeurIPS 2023 · 31 citations
- Offline Learning in Markov Games with General Function ApproximationAuthor 3 of 3ICML 2023 · 17 citations
- Reinforcement Learning in Low-rank MDPs with Density FeaturesAuthor 3 of 3ICML 2023 · 15 citations
- The Role of Coverage in Online Reinforcement LearningAuthor 4 of 4ICLR 2023 · 1 citation
- Towards Deployment-Efficient Reinforcement Learning: Lower Bound and OptimalityAuthor 5 of 6ICLR 2022 · 32 citations
- A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision ProcessesAuthor 4 of 4ICML 2022 · 31 citations
- On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RLAuthor 5 of 5NeurIPS 2022 · 31 citations
- Interaction-Grounded Learning with Action-Inclusive FeedbackAuthor 6 of 8NeurIPS 2022 · 12 citations
- Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring DistributionsAuthor 2 of 2NeurIPS 2022 · 9 citations
- Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant RegretAuthor 5 of 6NeurIPS 2022 · 4 citations
- Bellman-consistent Pessimism for Offline Reinforcement LearningAuthor 3 of 4NeurIPS 2021 · 339 citations
- Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement LearningAuthor 2 of 5NeurIPS 2021 · 207 citations
- Batch Value-function Approximation with Only RealizabilityAuthor 2 of 2ICML 2021 · 131 citations
- Towards Hyperparameter-free Policy Selection for Offline Reinforcement LearningAuthor 2 of 2NeurIPS 2021 · 47 citations
- Minimax Value Interval for Off-Policy Evaluation and Policy OptimizationAuthor 1 of 2NeurIPS 2020 · 68 citations
- From Importance Sampling to Doubly Robust Policy GradientAuthor 2 of 2ICML 2020 · 26 citations
