Sreejeet Maity

Ph.D. Student in Electrical Engineering · North Carolina State University · Raleigh, NC, U.S.A

I develop provably robust finite-sample guarantees for reinforcement learning (RL) under uncertainty and adversarial corruption. My current research interests include corruption-tolerant reinforcement learning, robust policy evaluation, distributed and federated reinforcement learning, and minimax lower bounds that characterize the fundamental limits of robust learning.

Google Scholar GitHub LinkedIn Download CV

Reinforcement Learning Statistical Learning Theory Control Theory Applied Probability Stochastic Approximation Algorithms Optimization Robust Statistics

Collaboration Note. I am always happy to engage with researchers working on broad areas of reinforcement learning, control theory, federated learning, and trustworthy machine learning. If you are interested in discussing possible collaborations or exchanging research ideas, please reach out to .

Prospective Opportunities. I will be entering the academic and industry research job market next year (2027), and I would be grateful to hear about opportunities aligned with my interests in broad areas of robust and safe RL, and reliable decision-making and control. I am also open to postdoctoral opportunities beginning in Fall 2027, as well as opportunities in subsequent academic cycles. Prospective recruiters, search committees, and researchers are warmly welcome to reach out.

Education

North Carolina State University

Ph.D. in Electrical Engineering · Aug 2023–Present · Raleigh, NC

Advisor: Dr. Aritra Mitra

Thesis: Towards a Finite-Time Theory of Adversarially Robust RL: Algorithms, Guarantees, and Fundamental Limits

Expected Graduation: December 2027–March 2028

Indian Institute of Science, Bangalore

M.Tech. in Robotics and Autonomous Systems · Aug 2021-June 2023 · Bangalore, India

Jadavpur University

B.E. in Electrical Engineering · Aug 2017-July 2021 · Kolkata, India

Research Experience

Graduate Research / Teaching Assistant

North Carolina State University · Aug 2023–Present · Raleigh, NC

Ph.D. Advisor: Dr. Aritra Mitra

Department of Electrical and Computer Engineering, North Carolina State University

• Robust optimal policy learning from corrupted and correlated observations. Showed that vanilla Q-learning is provably fragile under reward corruption, designed robust Bellman-update methods, and established finite-time convergence with matching minimax lower bounds. Results published at ICML 2026, IEEE CDC 2024, and IEEE CDC 2026, with related work presented at the NeurIPS 2025 Reliable ML Workshop and an extended theoretical investigation under review at Automatica.
• Robust policy evaluation under adversarial influences and Markovian data. Developed finite-time theory for robust temporal-difference learning with Markovian noise and function approximation, including upper bounds and near-tight lower bounds. Results published at AISTATS 2025, with further developments on near-optimal finite-time guarantees and fundamental statistical limits under review at L4DC 2027. We also investigated communication-efficient policy evaluation under finite-bit communication constraints, developing adaptive quantization methods with provable finite-time convergence guarantees. This work is under review at ECC 2027.
• Robust federated and multi-agent reinforcement learning. Developed adversarially robust and communication-efficient reinforcement learning algorithms for federated multi-agent settings, including Byzantine-resilient methods with collaborative speedups. Two papers published at ACC 2026, with further work on adversarially robust federated reinforcement learning under review at JMLR.

Research Collaboration · Decentralized Reinforcement Learning

University of California, San Diego · September 2025–Present · San Diego, CA

Research Collaborator: Prof. Robert W. Heath Jr.

Department of Electrical and Computer Engineering, University of California, San Diego

Decentralized Q-learning with asynchronous sampling and partial state-action coverage. Developing decentralized Q-learning algorithms that enable agents with partial state-action coverage to learn collaboratively from asynchronous observations. Establishing finite-time convergence guarantees and quantifying the benefits of variance reduction over static and time-varying communication networks. Result published at ACC 2026, with further developments on decentralized learning under asynchronous sampling and partial coverage under preparation for IEEE Transactions on Signal Processing (TSP).

Research Collaboration · Byzantine-Robust Representation Learning

Columbia University · May 2026–Present · New York, NY

Research Collaborator: Prof. James Anderson

Department of Electrical Engineering, Columbia University, New York

Byzantine-robust personalized federated policy evaluation with shared representations. Developing Byzantine-robust representation learning methods for heterogeneous reinforcement learning agents operating in distinct MDPs with temporally dependent data. The approach decomposes each agent's value function into a shared low-dimensional representation and a personalized local parameter, enabling collaborative learning of common structure while accommodating differences in transitions, rewards, policies, and value functions without persistent heterogeneity bias. This research is under review at Transactions on Machine Learning Research (TMLR).

List of Publications

[1] S. Maity^† and A. Mitra, “Corruption-Tolerant Optimal Asynchronous Q-Learning”, in International Conference on Machine Learning (ICML), 2026.

[2] S. Maity^† and A. Mitra, “Adversarially-Robust TD Learning with Markovian Data”, in International Conference on Artificial Intelligence and Statistics (AISTATS), 2025.

[3] S. Maity^† and A. Mitra, “Robust Asynchronous Q-Learning under Reward and State Corruption via Batching”, in IEEE Conference on Decision and Control (CDC), 2026.

[4] S. Maity^† and A. Mitra, “Robust Q-Learning under Corrupted Rewards”, in IEEE Conference on Decision and Control (CDC), 2024.

[5] S. Maity^† and A. Mitra, “Robust Federated Q-Learning with Almost No Communication”, in American Control Conference (ACC), 2026.

[6] S. Maity^†, F. Zhu, R. Heath, and A. Mitra, “Variance-Reduced Q-Learning over Static and Time-Varying Networks”, in American Control Conference (ACC), 2026.

[7] S. Maity^†, A. Mitra, “Batched Temporal-Difference Learning under Joint State and Reward Corruption”, in under review at Learning for Dynamics and Control(L4DC), 2027.

[8] S. Maity^†, A. Mitra, “Adaptive Quantization Preserves Fast Convergence in Temporal-Difference Learning over Rate-Limited Channels” in under review at European Control Conference (ECC), 2027.

[9] S. Maity^† and A. Mitra, “Learning from Unreliable Trajectories: Adversarially-Robust Federated Q-Learning”, under review at Journal of Machine Learning Reserach (JMLR).

[10] S. Maity^†, F. Zhu, R. Heath, and A. Mitra, “Decentralized Q-learning with Asynchronous Sampling and Partial Coverage”, Manuscript in preparation for IEEE Transactions on Signal Processing (TSP).

[11] S. Maity, L.Toso, J.Anderson, and A.Mitra, “Value Function Representation for Adversarially Robust Federated TD Learning”, under review at Transactions on Machine Learning Research (TMLR).

[12] S. Maity^†, A. Mitra, “Towards Minimax-Optimal Asynchronous Q-Learning from Corrupted Markovian Data”, under review at Automatica.

Projects

Federated MARL-GYM

We introduce a custom multi-agent reinforcement learning environment built with Gymnasium and Pygame, designed for evaluating federated RL (FRL) algorithms. The environment models a grid world where multiple agents navigate to accomplish spatially distributed tasks, like reaching delivery points.

Academic and Professional Service

• Head Teaching Assistant for ECE 516: Systems and Control Engineering and ECE 308: Elements of Control Systems, Department of Electrical and Computer Engineering, NC State.
• Served as a reviewer for 60+ papers in multiple flagship control/ ML venues, including the American Control Conference (ACC), the IEEE Conference on Decision and Control (CDC), Learning for Dynamics and Control (L4DC), Annual Conference on Neural Information Processing Systems(NeuRIPS), Artifical Intelligence and Statistics Conference (AISTATS), Journal of Machine Learning Research (JMLR), Transactions in Machine Learning Reserach (TMLR), IEEE Transactions in Automatic Control (TAC), Transactions in Signal and Information Processing over Networks (TSIPN), and Transactions in Signal Processing (TSP).

Awards

• ACC 2026 Travel Award May 2026
• L4DC Student Support Grant May 2025
• NESCW 2025 Student Support Grant May 2025
• IEEE CDC 2024 Student Support Award August 2024
• NC State ECE Student Research Support Award August 2024
• College of Engineering Graduate Merit Award 2023--24, 2024--25

Skills

Mathematics

Linear Algebra, Matrix Theory, Probability Theory, Random Process, Randomized Algorithms, Graph Theory, Analysis, Causal Inference, Bayesian Analysis, High-Dimensional Statistics, Stochastic Optimization.

Research

Reinforcement Learning, Statistical Learning Theory, Bandit Algorithms, Optimization, Information Theory, Control Theory, Stochastic Approximation, Robust Statistics, Distributed Networks.

Programming

Python, MATLAB, Simulink, C/C++.

Software and Libraries

PyTorch, TensorFlow, NumPy, Pandas, scikit-learn, Stable-Baselines3, CVXPY, CasADi, CleanRL, Gymnasium, MuJoCo.

Relevant Coursework

• Learning Theory: Theoretical Foundations of Large-Scale Machine Learning, Reinforcement Learning, Machine Learning for Signal Processing, Bayesian Learning, Physics Modelling with Neural Networks, Deep Learning and Neural Networks.
• Mathematics: Analysis I, Probability and Stochastic Processes, Stochastic Models and Applications, Convex Optimization for Data Science, Detection and Estimation Theory.
• Control Theory: Dynamics of Linear Systems, Networked and Distributed Control, Safety-Critical Control for Robotic Systems, Non-Linear Control Theory, Formal Analysis for Control Theory.