Thesis

• Reliable Decision-Making with Imprecise Models (Doctoral Dissertation)

  Sandhya Saisubramanian, University of Massachusetts Amherst.

Refereed Conferences/ Journals/ Workshop/ Technical Magazine Articles

• WOFOSTGym: A Crop Simulator for Learning Annual and Perennial Crop Management Strategies

  William Solow, Sandhya Saisubramanian, and Alan Fern. To appear in Proceedings of the Reinforcement Learning Conference (RLC), 2025.

• Mitigating Side Effects in Multi-Agent Systems Using Blame Assignment

  Pulkit Rustagi and Sandhya Saisubramanian. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2025. [Project Page]

• Multi-Objective Planning with Contextual Lexicographic Reward Preferences

  Pulkit Rustagi, Yashwanthi Anand, and Sandhya Saisubramanian. In Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2025. [Project Page]

• Verification and Validation of AI Systems Using Explanations

  Saaduddin Mahmud, Sandhya Saisubramanian, and Shlomo Zilberstein. In AAAI Fall Symposium on AI Trustworthiness and Risk Assessment for Challenging Contexts (ATRACC), 2024.

• Adaptive Feedback Selection for Learning to Avoid Negative Side Effects in Autonomous Agents

  Yashwanthi Anand and Sandhya Saisubramanian. In Workshop on Reinforcement Learning Beyond Rewards, Reinforcement Learning Conference (RLC), 2024.

• User-Aligned Assessment of Agent Learning and Operation for Reliable Autonomy

  Sandhya Saisubramanian. In AAAI Spring Symposium on User-Aligned Assessment of Adaptive AI Systems, 2024.

• Minimizing Negative Side Effects in Cooperative Multi-Agent Systems using Distributed Coordination

  Moumita Choudhury, Sandhya Saisubramanian, Hao Zhang, and Shlomo Zilberstein. In Proceedings of the 37th International FLAIRS Conference, 2024.

  *Also appeared as an extended abstract in proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2024.

• Explanation-Guided Reward Alignment

  Saaduddin Mahmud, Sandhya Saisubramanian, and Shlomo Zilberstein. In Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI), 2023.

• REVEALE: Reward Verification and Learning Using Explanations

  Saaduddin Mahmud, Sandhya Saisubramanian, and Shlomo Zilberstein. AAAI Workshop on Artificial Intelligence Safety, 2023. Nominated for Best Paper Award.

• Planning and Learning for Non-Markovian Negative Side Effects using Finite State Controllers

  Aishwarya Srivastava, Sandhya Saisubramanian, Praveen Paruchuri, Akshat Kumar, and Shlomo Zilberstein. In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI), 2023.

• Avoiding Negative Side Effects of Autonomous Systems in the Open World

  Sandhya Saisubramanian, Ece Kamar, and Shlomo Zilberstein. In the Journal of Artificial Intelligence Research (JAIR), 2022.

• Metareasoning for Safe Decision Making in Autonomous Systems

  Justin Svegliato, Connor Basich, Sandhya Saisubramanian, and Shlomo Zilberstein. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2022.

• Avoiding Negative Side Effects due to Incomplete Knowledge of AI Systems

  Sandhya Saisubramanian, Shlomo Zilberstein, and Ece Kamar. AI Magazine Winter 2022 edition.

• Learning to Generate Fair Clusters from Demonstrations

  Sainyam Galhotra, Sandhya Saisubramanian, and Shlomo Zilberstein. In Proceedings of AAAI/ACM Conference on Artificial Intelligence, Ethics and Society (AIES), 2021.

• Understanding User Attitudes Towards Negative Side Effects of AI Systems

  Sandhya Saisubramanian, Shannon C. Roberts, and Shlomo Zilberstein. In Proceedings of the ACM CHI Conference on Human Factors in Computing Systems, Late-Breaking Work Track, 2021.

• Mitigating Negative Side Effects via Environment Shaping (Extended Abstract)

  Sandhya Saisubramanian and Shlomo Zilberstein. In Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2021. [full paper]

• Using Metareasoning to Maintain and Restore Safety for Reliably Autonomy

  Justin Svegliato, Connor Basich, Sandhya Saisubramanian and Shlomo Zilberstein. IJCAI Workshop on Robust and Reliable Autonomy in the Wild (R2AW), 2021.

• Identifying Missing Features in State Representation for Safe Decision-Making

  Minori Narita, Sandhya Saisubramanian, Roderic A. Grupen and Shlomo Zilberstein. ICML Workshop on Human-AI Collaboration in Sequential Decision-Making, 2021.

• A Multi-Objective Approach to Mitigate Negative Side Effects

  Sandhya Saisubramanian, Ece Kamar, and Shlomo Zilberstein. In Proceedings of 29th International Joint Conference on Artificial Intelligence (IJCAI), 2020. Distinguished paper award.

• Balancing the Tradeoff Between Clustering Value and Interpretability

  Sandhya Saisubramanian*, Sainyam Galhotra*, and Shlomo Zilberstein. In Proceedings of AAAI/ACM Conference on Artificial Intelligence, Ethics and Society (AIES), 2020. (* equal contribution).

• Efficient Integration of Complementary Solvers for Quantum Circuit Compilation

  Sandhya Saisubramanian, Minh Do, Jeremy Frank, and Shlomo Zilberstein. ICAPS Workshop on Scheduling and Planning Applications (SPARK), 2020.

• Satisfying Social Preferences in Ridesharing Services

  Sandhya Saisubramanian, Connor Basich, Shlomo Zilberstein, and Claudia Goldman. In Proceedings of IEEE Intelligent Transportation Systems Conference (ITSC), 2019.

• Adaptive Outcome Selection for Planning With Reduced Models

  Sandhya Saisubramanian and Shlomo Zilberstein. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019.

• Planning in Stochastic Environments with Goal Uncertainty

  Sandhya Saisubramanian, Kyle Hollins Wray, Luis Pineda, and Shlomo Zilberstein. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019.

• The Value of Incorporating Social Preferences in Dynamic Ridesharing

  Sandhya Saisubramanian, Connor Basich, Shlomo Zilberstein, and Claudia Goldman. ICAPS Workshop on Scheduling and Planning Applications (SPARK), 2019.

• Minimizing the Negative Side Effects of Planning with Reduced Models

  Sandhya Saisubramanian and Shlomo Zilberstein. AAAI Workshop on Artificial Intelligence Safety, 2019.

• Planning Using a Portfolio of Reduced Models (Extended Abstract)

  Sandhya Saisubramanian, Shlomo Zilberstein, and Prashant Shenoy. In Proceedings of 17th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2018.

• Safe Reduced Models for Probabilistic Planning

  Sandhya Saisubramanian and Shlomo Zilberstein. ICML/IJCAI/AAMAS Workshop on Planning and Learning (PAL), 2018.

• Optimizing Electric Vehicle Charging Through Determinization

  Sandhya Saisubramanian, Shlomo Zilberstein, and Prashant Shenoy. ICAPS Workshop on Scheduling and Planning Applications (SPARK), 2017.

• Risk Based Optimization for Emergency Medical Systems

  Sandhya Saisubramanian, Pradeep Varakantham, and Hoong Chuin Lau. In Proceedings of 29th AAAI Conference on Artificial Intelligence (AAAI), 2015.

• STREETS: Game-Theoretic Traffic Patrolling with Exploration and Exploitation

  Matthew Brown, Sandhya Saisubramanian, Pradeep Varakantham, and Milind Tambe. In Proceedings of Innovative Applications in Artificial Intelligence (IAAI) at 28th AAAI Conference on Artificial Intelligence, 2014.