Sandhya Saisubramanian
University of Massachusetts Amherst
H-index: 10
North America-United States
Top articles of Sandhya Saisubramanian
Planning and learning for reliable autonomy in the open world
Proceedings of the AAAI Conference on Artificial Intelligence
2023/6/26
Sandhya Saisubramanian
H-Index: 5
Explanation-Guided Reward Alignment
2023
Planning and Learning for Non-Markovian Negative Side Effects Using Finite State Controllers
Proceedings of the AAAI Conference on Artificial Intelligence
2023/6/26
Aishwarya Srivastava
H-Index: 2
Sandhya Saisubramanian
H-Index: 5
Praveen Paruchuri
H-Index: 11
Akshat Kumar
H-Index: 3
Shlomo Zilberstein
H-Index: 30
Reliable Decision-Making with Imprecise Models
2022
Sandhya Saisubramanian
H-Index: 5
Avoiding negative side effects due to incomplete knowledge of AI systems
AI Magazine
2022/1/18
Sandhya Saisubramanian
H-Index: 5
Shlomo Zilberstein
H-Index: 30
Avoiding negative side effects of autonomous systems in the open world
Journal of Artificial Intelligence Research
2022/5/10
Sandhya Saisubramanian
H-Index: 5
Shlomo Zilberstein
H-Index: 30
Metareasoning for safe decision making in autonomous systems
2022
Justin Svegliato
H-Index: 4
Connor Basich
H-Index: 1
Sandhya Saisubramanian
H-Index: 5
Shlomo Zilberstein
H-Index: 30
Reveale: Reward verification and learning using explanations
2022
Understanding user attitudes towards negative side effects of AI systems
2021/5/8
Mitigating Negative Side Effects via Environment Shaping
arXiv preprint arXiv:2102.07017
2021/2/13
Sandhya Saisubramanian
H-Index: 5
Shlomo Zilberstein
H-Index: 30
Learning to Generate Fair Clusters from Demonstrations
2021/7/21
Using Metareasoning to Maintain and Restore Safety for Reliably Autonomy
2021
Justin Svegliato
H-Index: 4
Connor Basich
H-Index: 1
Sandhya Saisubramanian
H-Index: 5
Shlomo Zilberstein
H-Index: 30
Efficient Integration of Complementary Solvers for Quantum Circuit Compilation
2020
Sandhya Saisubramanian
H-Index: 5
Shlomo Zilberstein
H-Index: 30
A Multi-Objective Approach to Mitigate Negative Side Effects
2021/1/7
Sandhya Saisubramanian
H-Index: 5
Shlomo Zilberstein
H-Index: 30
Mitigating the Negative Side Effects of Reasoning with Imperfect Models: A Multi-Objective Approach
2020/5/5
Sandhya Saisubramanian
H-Index: 5
Shlomo Zilberstein
H-Index: 30
Balancing the Tradeoff Between Clustering Value and Interpretability
2020/2/7
Co-Authors
