Publications

Kishor Jothimurugan, Suguman Bansal, Osbert Bastani, Rajeev Alur (2025). Specification-Guided Reinforcement Learning. International Conference on Neuro-symbolic Systems (NeuS).

Cite PDF

Kishor Jothimurugan, Steve Hsu, Osbert Bastani, Rajeev Alur (2023). Robust Subtask Leaning for Compositional Generalization. International Conference on Machine Learning (ICML).

Cite PDF ArXiv Code

Rajeev Alur, Osbert Bastani, Kishor Jothimurugan, Mateo Perez, Fabio Somenzi, Ashutosh Trivedi (2023). Policy Synthesis and Reinforcement Learning for Discounted LTL. International Conference on Computer Aided Verification (CAV).

Cite PDF ArXiv

Kishor Jothimurugan, Suguman Bansal, Osbert Bastani, Rajeev Alur (2022). Specification-Guided Learning of Nash Equilibria with High Social Welfare. International Conference on Computer Aided Verification (CAV).

Cite PDF ArXiv Code Slides

Rajeev Alur, Suguman Bansal, Osbert Bastani, Kishor Jothimurugan (2022). A Framework for Transforming Specifications in Reinforcement Learning. Springer Festschrift in honor of Prof. Tom Henzinger.

Cite PDF ArXiv Slides

Kishor Jothimurugan, Suguman Bansal, Osbert Bastani, Rajeev Alur (2021). Compositional Reinforcement Learning from Logical Specifications. Advances in Neural Information Processing Systems (NeurIPS).

Cite PDF ArXiv Code

Radoslav Ivanov, Kishor Jothimurugan, Steve Hsu, Shaan Vaidya, Rajeev Alur, Osbert Bastani (2021). Compositional Learning and Verification of Neural Network Controllers. International Conference on Embedded Software (EMSOFT).

Cite PDF Code Slides

Kishor Jothimurugan, Osbert Bastani, Rajeev Alur (2021). Abstract Value Iteration for Hierarchical Reinforcement Learning. International Conference on Artificial Intelligence and Statistics (AISTATS).

Cite PDF ArXiv Code Slides Talk

Rajeev Alur, Yu Chen, Kishor Jothimurugan, Sanjeev Khanna (2020). Space-efficient Query Evaluation over Probabilistic Event Streams. ACM/IEEE Symposium on Logic in Computer Science (LICS).

Cite PDF Slides

Kishor Jothimurugan, Rajeev Alur, Osbert Bastani (2019). A Composable Specification Language for Reinforcement Learning Tasks. Advances in Neural Information Processing Systems (NeurIPS).

Cite PDF ArXiv Code Slides