Publications

[P2] M. Jafarnia-Jahromi, R. Jain, A. Nayyar  ‘Learning zero-sum stochastic games with posterior sampling’.  pdf

[P1] M. Jafarnia-Jahromi, C. Wei, R. Jain, H. Luo ‘A Model-free Learning Algorithm for Infinite-horizon Average-reward MDPs with Near-optimal Regret’.  pdf

[C8] M. Jafarnia-Jahromi, L. Chen, R. Jain, H. Luo ‘Posterior Sampling-Based Online Learning for the Stochastic Shortest Path model’, UAI 2023.  pdf

[C7] W. Chang, M. Jafarnia-Jahromi, R. Jain  ‘Online learning for cooperative multi-player multi-armed bandits’, CDC 2022.  pdf

[C6]  M. Jafarnia-Jahromi, R. Jain, A. Nayyar ‘Online learning for unknown partially observable MDPs’, AISTATS 2022. pdf

[C5] L. Chen, M. Jafarnia-Jahromi, R. Jain, H. Luo  ‘Implicit finite-horizon approximation and efficient optimal algorithms for Stochastic Shortest Path’, NeurIPS 2021.  pdf

[C4] C. Wei, M. Jafarnia-Jahromi, H. Luo, R. Jain ‘Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation’, AISTATS 2021. pdf

[C3] C. Wei, M. Jafarnia-Jahromi, H. Luo, H. Sharma, R. Jain ‘Model-free reinforcement learning in infinite-horizon average-reward Markov Decision Processes’, ICML 2020. pdf

[C2] H. Sharma, M. Jafarnia-Jahromi, R. Jain ‘Approximate relative value learning for average-reward continuous state MDPs’, UAI 2019. pdf

[C1] M. Jafarnia-Jahromi, T. Chowdhury, H. Wu, S. Mukherjee ‘PPD: Permutation phase defense against adversarial examples in deep learning’, ICMLA 2019. pdf

[J1] M. Jafarnia-Jahromi and R. Jain, ‘Non-indexability of the stochastic appointment scheduling problem’, Automatica 118 (2020), 109016.  pdf