|
Publications
Recent Publications (from 2025)
Books
L.A.Prashanth and S.Bhatnagar, Gradient-based Algorithms for Zeroth Order Optimization, Frontiers and Trends in Optimization, NOW Publishers, 2025 prepublication draft
Journal Papers
L.Mandal and S.Bhatnagar, Optimizing Successive Over-relaxation Q-learning with Deterministic Perturbation Gradient Search, IEEE Transactions on Artificial Intelligence, Aug 2025 (accepted)
S.Bhatnagar and Deepak H.R., Variance Reduced Smoothed Functional REINFORCE Policy Gradient Algorithms, Transactions on Machine Learning Research (TMLR), July 2025 (accepted)
S.Guin, V.S.Borkar, and S.Bhatnagar, An Actor-Critic Algorithm with Function Approximation for Risk
Sensitive Cost Markov Decision Processes, IEEE Transactions on Automatic Control (accepted) July 2025 online PDF, arXiv
L.Mandal and S.Bhatnagar, n-Step Temporal Difference Learning with Optimal n, Vol. 179, Article 112449 (9 pages), Automatica,
2025 online PDF, arXiv
S.Pachal, S.Bhatnagar, and L.A.Prashanth, Generalized Simultaneous Perturbation-based Gradient Search with
Reduced Estimator Bias, IEEE Transactions on Automatic Control, Vol.70, No.7, pp.4687-4702, 2025 online PDF, arXiv
Preprints Submitted to journals
Our recent papers on arXiv can be found here
Proceedings of International Conferences
P.Dutta, M.Ayyoob, S.Bhatnagar, and A.Dukkipati, One Encoder to Rule them All: Representation Learning for Model-free Visual Reinforcement Learning using Fourier Neural Operators,
International Conference on Computer Vision (ICCV), Honolulu, Hawaii, Oct.19-23, 2025
P.Panda and S.Bhatnagar, Two-Timescale Critic-Actor for Average Reward MDPs with Function Approximation, AAAI,
Philadelphia, USA, Feb 27-March 4, 2025 (accepted) arXiv
|