He Zhu
Assistant Professor
Computer Science Department
Rutgers University, New Brunswick
Email: hz375@cs.rutgers.edu
[Awards] [Service] [Teaching] [Publications]
Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning [pdf]
|
Learning World Models for Unconstrained Goal Navigation [pdf]
|
Safe Exploration in Reinforcement Learning by Reachability Analysis over Learned Models [pdf]
|
Reward-guided Synthesis of Intelligent Agents with Control Structures [pdf]
|
Instructing Goal-Conditioned Reinforcement Learning Agents with Temporal Logic Objectives [pdf]
|
Verification-guided Programmatic Controller Synthesis [pdf]
|
ReLAX: Reinforcement Learning Agent Explainer for Arbitrary Predictive Models [pdf]
|
Learn Basic Skills and Reuse: Modularized Adaptive Neural Architecture Search (MANAS) [pdf]
|
Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising [pdf]
|
Programmatic Reinforcement Learning without Oracles [pdf]
|
Graph Collaborative Reasoning [pdf]
|
Differentiable Synthesis of Program Architectures [pdf]
|
ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks [pdf]
|
An Inductive Synthesis Framework for Verifiable Reinforcement Learning [pdf][code]
|
A Data-Driven CHC Solver [pdf][code]
|
Automatically Learning Shape Specifications [pdf][code]
|
Learning Refinement Types [pdf][code]
|
Poling: SMT Aided Linearizability Proofs [pdf]
|
Dependent Array Type Inference from Tests [pdf]
|
Compositional and Lightweight Dependent Type Inference for ML [pdf]
|