Safe Exploration in Reinforcement Learning by Reachability Analysis over Learned Models Y Wang, H Zhu International Conference on Computer Aided Verification, 232-255, 2024 | | 2024 |
AutoFlow: Automated Workflow Generation for Large Language Model Agents Z Li, S Xu, K Mei, W Hua, B Rama, O Raheja, H Wang, H Zhu, Y Zhang arXiv preprint arXiv:2407.12821, 2024 | | 2024 |
Reward-Guided Synthesis of Intelligent Agents with Control Structures G Cui, Y Wang, W Qiu, H Zhu Proceedings of the ACM on Programming Languages 8 (PLDI), 1730-1754, 2024 | | 2024 |
Instructing goal-conditioned reinforcement learning agents with temporal logic objectives W Qiu, W Mao, H Zhu Advances in Neural Information Processing Systems 36, 2024 | | 2024 |
Verification-guided programmatic controller synthesis Y Wang, H Zhu International Conference on Tools and Algorithms for the Construction and …, 2023 | 3 | 2023 |
Explain the explainer: Interpreting model-agnostic counterfactual explanations of a deep reinforcement learning agent Z Chen, F Silvestri, G Tolomei, J Wang, H Zhu, H Ahn IEEE Transactions on Artificial Intelligence 5 (4), 1443-1457, 2022 | 18 | 2022 |
Learn basic skills and reuse: Modularized adaptive neural architecture search (manas) H Chen, Y Li, H Zhu, Y Zhang Proceedings of the 31st ACM International Conference on Information …, 2022 | 7 | 2022 |
ReLAX: Reinforcement Learning Agent Explainer for Arbitrary Predictive Models Z Chen, F Silvestri, J Wang, H Zhu, H Ahn, G Tolomei Proceedings of the 31st ACM international conference on information …, 2022 | 42* | 2022 |
Defending observation attacks in deep reinforcement learning via detection and denoising Z Xiong, J Eappen, H Zhu, S Jagannathan Joint European Conference on Machine Learning and Knowledge Discovery in …, 2022 | 7 | 2022 |
Programmatic reinforcement learning without oracles W Qiu, H Zhu The Tenth International Conference on Learning Representations, 2022 | 38 | 2022 |
Graph collaborative reasoning H Chen, Y Li, S Shi, S Liu, H Zhu, Y Zhang Proceedings of the Fifteenth ACM International Conference on Web Search and …, 2022 | 40 | 2022 |
Differentiable synthesis of program architectures G Cui, H Zhu Advances in Neural Information Processing Systems 34, 11123-11135, 2021 | 18 | 2021 |
Robustness to adversarial attacks in learning-enabled controllers Z Xiong, J Eappen, H Zhu, S Jagannathan arXiv preprint arXiv:2006.06861, 2020 | 6 | 2020 |
ART: abstraction refinement-guided training for provably correct neural networks X Lin, H Zhu, R Samanta, S Jagannathan # PLACEHOLDER_PARENT_METADATA_VALUE# 1, 148-157, 2020 | 31 | 2020 |
An inductive synthesis framework for verifiable reinforcement learning H Zhu, Z Xiong, S Magill, S Jagannathan Proceedings of the 40th ACM SIGPLAN conference on programming language …, 2019 | 114 | 2019 |
A data-driven CHC solver H Zhu, S Magill, S Jagannathan ACM SIGPLAN Notices 53 (4), 707-721, 2018 | 97 | 2018 |
Automatically learning shape specifications H Zhu, G Petri, S Jagannathan Proceedings of the 37th ACM SIGPLAN Conference on Programming Language …, 2016 | 38 | 2016 |
Learning to verify the heap M Brockschmidt, Y Chen, B Cook, P Kohli, S Krishna, D Tarlow, H Zhu Technical Report, 2016 | 4 | 2016 |
Learning Program Specifications from Sample Runs H Zhu Purdue University, 2016 | | 2016 |
Learning refinement types H Zhu, AV Nori, S Jagannathan ACM SIGPLAN Notices 50 (9), 400-411, 2015 | 36 | 2015 |