Yali Du

7

Papers

14

Total Citations

Papers (7)

RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors

Self-Verifying Reflection Helps Transformers with CoT Reasoning

NeurIPS 2025arXiv

Abstract Counterfactuals for Language Model Agents

Social World Model-Augmented Mechanism Design Policy Learning

STAS: Spatial-Temporal Return Decomposition for Multi-Agent Reinforcement Learning

TAPE: Leveraging Agent Topology for Cooperative Multi-Agent Policy Gradient

PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation