Zongzhang Zhang

5

Papers

42

Total Citations

Papers (5)

ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning

Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations

EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving

Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics

Deep Demonstration Tracing: Learning Generalizable Imitator Policy for Runtime Imitation from a Single Demonstration