publications

Publications Thesis

publications

2026

  1. CACM
    Specification-Guided Reinforcement Learning
    Rajeev Alur, Suguman Bansal, Osbert Bastani, and Kishor Jothimurugan
    Communications of the ACM (CACM), 2026
    PDF

2025

  1. GenPlan
    Certification-Guided Evaluation of Reinforcement Learning Generalization
    Vignesh Subramanian, Djordje Zikelic, and Suguman Bansal
    AAAI 2025 Workshop on Generalization in Planning (GenPlan), 2025
    PDF
  2. ATVA
    Inductive Generalization in Reinforcement Learning from Specifications
    Vignesh Subramanian, Rohit Kushwah, Subhajit Roy, and Suguman Bansal
    In Automated Technology for Verification and Analysis (ATVA), 2025
    PDF
  3. CAV
    INTERLEAVE: A Faster Symbolic Algorithm for Maximal End Component Decomposition
    Suguman Bansal and Ramneet Singh
    In Computer Aided Verification (CAV), 2025
    PDF
  4. NeuS
    Specification-Guided Reinforcement Learning
    Kishor Jothimurugan, Suguman Bansal, Osbert Bastani, and Rajeev Alur
    In International Conference on Neuro-symbolic Systems (NeuS), 2025
    PDF

2024

  1. FMCAD
    DAG-Based Compositional Approaches for LTLf to DFA Conversions
    Suguman Bansal, Yash Kankariya, and Yong Li
    In Formal Methods in Computer-Aided Design (FMCAD), 2024
    PDF
  2. ICML
    Reinforcement Learning from Reachability Specifications: PAC Guarantees with Expected Conditional Distance
    Jakub Svoboda, Suguman Bansal, and Krishnendu Chatterjee
    In International Conference on Machine Learning (ICML), 2024
    PDF

2023

  1. SIGLOG
    Automata-Based Quantitative Reasoning
    Suguman Bansal
    ACM SIGLOG News, 2023
    PDF
  2. ATVA
    Model Checking Strategies from Synthesis over Finite Traces
    Suguman Bansal, Yong Li, Lucas M. Tabajara, Moshe Y. Vardi, and Andrew M. Wells
    In Automated Technology for Verification and Analysis (ATVA), 2023
    Best Paper Award PDF
  3. IJCAI
    Multi-Agent Systems with Quantitative Satisficing Goals
    Senthil Rajasekaran, Suguman Bansal, and Moshe Y. Vardi
    In International Joint Conference on Artificial Intelligence (IJCAI), 2023
    PDF

2022

  1. LMCS
    Comparator automata in quantitative verification
    Suguman Bansal, Swarat Chaudhuri, and Moshe Y. Vardi
    Log. Methods Comput. Sci., 2022
    PDF
  2. AAAI
    Synthesis from Satisficing and Temporal Goals
    Suguman Bansal, Lydia E. Kavraki, Moshe Y. Vardi, and Andrew M. Wells
    In AAAI Conference on Artificial Intelligence (AAAI), 2022
    PDF
  3. Henzinger-60
    A Framework for Transforming Specifications in Reinforcement Learning
    Rajeev Alur, Suguman Bansal, Osbert Bastani, and Kishor Jothimurugan
    In Principles of Systems Design, 2022
    PDF
  4. CAV
    Specification-Guided Learning of Nash Equilibria with High Social Welfare
    Kishor Jothimurugan, Suguman Bansal, Osbert Bastani, and Rajeev Alur
    In Computer Aided Verification (CAV), 2022
    PDF
  5. SAS
    Specification-Guided Reinforcement Learning
    Suguman Bansal
    In Static Analysis Symposium (SAS), 2022
    PDF
  6. VSTTE
    Compositional Safety LTL Synthesis
    Suguman Bansal, Giuseppe De Giacomo, Antonio Di Stasio, Yong Li, Moshe Y. Vardi, and Shufang Zhu
    In Verified Software: Theories, Tools, and Experiments (VSTTE), 2022
    PDF

2021

  1. CAV
    Adapting Behaviors via Reactive Synthesis
    Gal Amram, Suguman Bansal, Dror Fried, Lucas Martinelli Tabajara, Moshe Y. Vardi, and Gera Weiss
    In Computer Aided Verification (CAV), 2021
    PDF
  2. NeurIPS
    Compositional Reinforcement Learning from Logical Specifications
    Kishor Jothimurugan, Suguman Bansal, Osbert Bastani, and Rajeev Alur
    In Neural Information Processing Systems (NeurIPS), 2021
    PDF
  3. TACAS
    On Satisficing in Quantitative Games
    Suguman Bansal, Krishnendu Chatterjee, and Moshe Y. Vardi
    In Tools and Algorithms for the Construction and Analysis of Systems (TACAS), 2021
    PDF

2020

  1. POPL
    Synthesis of coordination programs from linear temporal specifications
    Suguman Bansal, Kedar S. Namjoshi, and Yaniv Sa’ar
    Proc. ACM Program. Lang., 2020
    PDF
  2. AAAI
    Hybrid Compositional Reasoning for Reactive Synthesis from Finite-Horizon Specifications
    Suguman Bansal, Yong Li, Lucas M. Tabajara, and Moshe Y. Vardi
    In AAAI Conference on Artificial Intelligence (AAAI), 2020
    PDF

2019

  1. CAV
    Safety and Co-safety Comparator Automata for Discounted-Sum Inclusion
    Suguman Bansal and Moshe Y. Vardi
    In Computer Aided Verification (CAV), 2019
    PDF

2018

  1. CAV
    Automata vs Linear-Programming Discounted-Sum Inclusion
    Suguman Bansal, Swarat Chaudhuri, and Moshe Y. Vardi
    In Computer Aided Verification (CAV), 2018
    PDF
  2. CAV
    Synthesis of Asynchronous Reactive Programs from Temporal Specifications
    Suguman Bansal, Kedar S. Namjoshi, and Yaniv Sa’ar
    In Computer Aided Verification (CAV), 2018
    PDF
  3. FoSSaCS
    Comparator Automata in Quantitative Verification
    Suguman Bansal, Swarat Chaudhuri, and Moshe Y. Vardi
    In Foundations of Software Science and Computation Structures (FOSSACS), 2018
    PDF

↑ Return to top

thesis

2020

  1. PhD Thesis
    Automata-Based Quantitative Verification
    Suguman Bansal
    Rice University, 2020
    HTML

2016

  1. Masters Thesis
    Algorithmic Analysis of Regular Repeated Games
    Suguman Bansal
    Rice University, 2016
    HTML

↑ Return to top