9 papers
One-Step Bellman Alignment Enables Provably Efficient Transfer in Online RL
Elynn Chen, Enpei Zhang, Jinhang Chai +1
We study online transfer reinforcement learning (RL) in episodic Markov decision processes, where experience from related source tasks is available during learning on a target task…
SMART Fine-tuning Factor Augmented Neural Lasso
Jinhang Chai, Jianqing Fan, Cheng Gao +1
Fine-tuning is a widely used strategy for adapting pre-trained models to new tasks, yet its methodology and theoretical properties in high-dimensional nonparametric settings with v…
Optimal Semiparametric Dynamic Pricing with Feature Diversity
Jinhang Chai, Yaqi Duan, Jianqing Fan +1
We study contextual dynamic pricing under a semiparametric demand model in which the purchase probability is , where captures mean utility as…
Neural Generative Distributional Regression
Jinhang Chai, Jianqing Fan, Yihong Gu
Any continuous conditional distribution of given can be generated from a transform of a known noise distribution such as the uniform or normal distribution via $Y = g(X…
Low-Rank Plus Sparse Matrix Transfer Learning under Growing Representations and Ambient Dimensions
Jinhang Chai, Xuyuan Liu, Elynn Chen +1
Learning systems often expand their ambient features or latent representations over time, embedding earlier representations into larger spaces with limited new latent structure. We…
Deep Transfer -Learning for Offline Non-Stationary Reinforcement Learning
Jinhang Chai, Elynn Chen, Jianqing Fan
In dynamic decision-making scenarios across business and healthcare, leveraging sample trajectories from diverse populations can significantly enhance reinforcement learning (RL) p…