Chi Jin

papers

951

total citations

papers (17)

Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms

NEURIPS 2021arXiv

242

citations

Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent

NEURIPS 2022arXiv

citations

Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL

NEURIPS 2023arXiv

citations

Tuning-Free Stochastic Optimization

ICML 2024arXiv

citations

FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning

ICML 2024arXiv

citations

Learning World Models for Interactive Video Generation

NEURIPS 2025arXiv

citations

DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization

ICCV 2025arXiv

citations

Context-lumpable stochastic bandits

NEURIPS 2023arXiv

citations

Is RLHF More Difficult than Standard RL? A Theoretical Perspective

NEURIPS 2023

citations

Provably Efficient Reinforcement Learning with Kernel and Neural Function Approximations

NEURIPS 2020

citations

Chi Jin

papers (17)

Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms

On the Theory of Transfer Learning: The Importance of Task Diversity

Near-Optimal Reinforcement Learning with Self-Play

Sample-Efficient Reinforcement Learning of Undercomplete POMDPs

Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games

DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method

Sample-Efficient Reinforcement Learning of Partially Observable Markov Games

On the Provable Advantage of Unsupervised Pretraining

Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent

Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL

Tuning-Free Stochastic Optimization

FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning

Learning World Models for Interactive Video Generation

DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization

Context-lumpable stochastic bandits

Is RLHF More Difficult than Standard RL? A Theoretical Perspective

Provably Efficient Reinforcement Learning with Kernel and Neural Function Approximations

papers (17)

Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms

On the Theory of Transfer Learning: The Importance of Task Diversity

Near-Optimal Reinforcement Learning with Self-Play

Sample-Efficient Reinforcement Learning of Undercomplete POMDPs

Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games

DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method

Sample-Efficient Reinforcement Learning of Partially Observable Markov Games

On the Provable Advantage of Unsupervised Pretraining

Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent

Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL

Tuning-Free Stochastic Optimization

FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning

Learning World Models for Interactive Video Generation

DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization

Context-lumpable stochastic bandits

Is RLHF More Difficult than Standard RL? A Theoretical Perspective

Provably Efficient Reinforcement Learning with Kernel and Neural Function Approximations