Picture for Dongruo Zhou

Dongruo Zhou

Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models

Add code
Mar 20, 2025
Viaarxiv icon

Provable Zero-Shot Generalization in Offline Reinforcement Learning

Add code
Mar 11, 2025
Viaarxiv icon

Breaking the $\log(1/Δ_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids

Add code
Jan 29, 2025
Figure 1 for Breaking the $\log(1/Δ_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids
Figure 2 for Breaking the $\log(1/Δ_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids
Viaarxiv icon

Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learning

Add code
Oct 30, 2024
Viaarxiv icon

CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing

Add code
Oct 22, 2024
Figure 1 for CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing
Figure 2 for CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing
Figure 3 for CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing
Figure 4 for CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing
Viaarxiv icon

Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds

Add code
Aug 16, 2024
Viaarxiv icon

Uncertainty-Aware Reward-Free Exploration with General Function Approximation

Add code
Jun 24, 2024
Figure 1 for Uncertainty-Aware Reward-Free Exploration with General Function Approximation
Figure 2 for Uncertainty-Aware Reward-Free Exploration with General Function Approximation
Figure 3 for Uncertainty-Aware Reward-Free Exploration with General Function Approximation
Figure 4 for Uncertainty-Aware Reward-Free Exploration with General Function Approximation
Viaarxiv icon

Variance-Dependent Regret Bounds for Non-stationary Linear Bandits

Add code
Mar 15, 2024
Viaarxiv icon

DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training

Add code
Mar 05, 2024
Figure 1 for DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training
Figure 2 for DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training
Figure 3 for DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training
Figure 4 for DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training
Viaarxiv icon

Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path

Add code
Feb 14, 2024
Figure 1 for Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path
Figure 2 for Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path
Figure 3 for Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path
Viaarxiv icon