Preprints

1. Honghao Wei, Arnob Ghosh,Xingyu Zhou, Lei Ying, and Ness Shroff,“Provably Efficient Model-Free RL Algorithm for Non-Stationary Constrained Markov Decision Process”, Submitted in International Conference on Artificial Intelligence and Statistics (AISTATS), 2023.

2. Arnob Ghosh, Xingyu Zhou, and Ness Shroff, “Achieving Sub-linear Regret in Infinite Horizon Average Reward Constrained MDP with Linear Function Approximation”, Submitted in International Conference on Learning Representation (ICLR’2022).

3. Arnob Ghosh, “Provably Efficient Model-free RL for Stackelberg game with Linear Function Approximation”, Submitted in AAAI’2023.

4. Arnob Ghosh, and Vaneet Aggarwal, “ Model-free Reinforcement Learning for Leader Follower Mean Field Game”, submitted in, Journal of Machine Learning Research (JMLR), August’2022.