Sourav Ganguly

According to our database, Sourav Ganguly authored at least 8 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Optimistic Policy Learning under Pessimistic Adversaries with Regret and Violation Guarantees.

Sourav Ganguly, Kartik Pandit, Arnob Ghosh

CoRR, April, 2026

2025

Provably Efficient Sample Complexity for Robust CMDP.

Sourav Ganguly, Arnob Ghosh

CoRR, November, 2025

Certifiable Safe RLHF: Fixed-Penalty Constraint Optimization for Safer Language Models.

Kartik Pandit, Sourav Ganguly, Arnesh Banerjee, Shaahin Angizi, Arnob Ghosh

CoRR, October, 2025

Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees.

Sourav Ganguly, Arnob Ghosh, Kishan Panaganti, Adam Wierman

CoRR, May, 2025

Iteration Complexity for Robust CMDP for finite policy space.

Sourav Ganguly, Arnob Ghosh

Proceedings of the 64th IEEE Conference on Decision and Control, 2025

2024

Restricted Bayesian Neural Network.

Sourav Ganguly

CoRR, 2024

2023

Efficient Off-Policy Algorithms for Structured Markov Decision Processes.

Sourav Ganguly, Raghuram Bharadwaj Diddigi, Prabuchandran K. J.

Proceedings of the 62nd IEEE Conference on Decision and Control, 2023

2022

Data Efficient Safe Reinforcement Learning.

Sindhu Padakandla, Prabuchandran K. J., Sourav Ganguly, Shalabh Bhatnagar

Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, 2022