Nan Jiang

35

Papers

150

Total Citations

1

Affiliations

Affiliations

The University of Chicago

Papers (35)

Repeated Inverse Reinforcement Learning

NeurIPS 2017arXiv

F-HOI: Toward Fine-grained Semantic-Aligned 3D Human-Object Interactions

GameArena: Evaluating LLM Reasoning through Live Computer Games

Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability

Racing Control Variable Genetic Programming for Symbolic Regression

LATTE: Improving Latex Recognition for Tables and Formulae with Iterative Refinement

Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol

A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning

Solving Satisfiability Modulo Counting for Symbolic and Statistical AI Integration with Provable Guarantees

Full-Body Articulated Human-Object Interaction

Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint

Active Symbolic Discovery of Ordinary Differential Equations via Phase Portrait Sketching

Scaling Up Dynamic Human-Scene Interaction Modeling

Dynamic Motion Blending for Versatile Motion Editing

Adversarial Model for Offline Reinforcement Learning

Future-Dependent Value-Based Off-Policy Evaluation in POMDPs

Abstraction Selection in Model-based Reinforcement Learning

Doubly Robust Off-policy Value Evaluation for Reinforcement Learning

Contextual Decision Processes with low Bellman rank are PAC-Learnable

Hierarchical Imitation and Reinforcement Learning

Information-Theoretic Considerations in Batch Reinforcement Learning

Provably efficient RL with Rich Observations via Latent State Decoding

Completing State Representations using Spectral Learning

On Oracle-Efficient PAC RL with Rich Observations

Provably Efficient Q-Learning with Low Switching Cost

Minimax Value Interval for Off-Policy Evaluation and Policy Optimization

When Counterpoint Meets Chinese Folk Melodies

Bellman-consistent Pessimism for Offline Reinforcement Learning

Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning

Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning

Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret

Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions

Interaction-Grounded Learning with Action-Inclusive Feedback

On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL

A Few Expert Queries Suffices for Sample-Efficient RL with Resets and Linear Value Approximation