♦️ Selected First-Authored Publications

[\(C_5\)] Corruption-Tolerant Optimal Asynchronous Q-Learning

Sreejeet Maity^†, Aritra Mitra

International Conference on Machine Learning, ICML 2026.

Summary Paper Poster Slides Code

[\(C_4\)] Adversarially-Robust TD Learning with Markovian Data: Finite-Time Rates and Fundamental Limits

Sreejeet Maity^†, Aritra Mitra

International Conference on Artificial Intelligence and Statistics, AISTATS 2025.

Summary Paper Poster Slides Code

[\(C_3\)] Robust Q-Learning under Corrupted Rewards

Sreejeet Maity^†, Aritra Mitra

IEEE Conference on Decision and Control, CDC 2024.

Summary Paper Poster Slides Code

[\(C_2\)] Robust Federated Q-Learning with Almost No Communication

Sreejeet Maity^†, Aritra Mitra

American Control Conference, ACC 2026.

Summary Paper Poster Slides Code

[\(C_1\)] Variance-Reduced Q-Learning over Static and Time-Varying Networks

Sreejeet Maity^†, Feng Zhu, Robert Heath, Aritra Mitra

American Control Conference, ACC 2026.

Summary Paper Poster Slides Code

♠️ Accepted Workshop Presentations

1. Multi-Agent Robust FRL with Sparse Communication, NCSU Robotics Symposium 2026.
2. Agnostic Q-Learning under corrupted Feedback, NeurIPS 2025 Reliable ML Workshop.
3. Robust Federated RL with Byzantine Agents, Applied AI Symposium 2025, NESCW 2026.
4. Theoretical Limits of Robust TD Learning, New York RL Workshop, NYRL 2025, Amazon.
5. Towards Finite-Time Theory for Adversarially-Robust RL, NESCW 2025.
6. Adversarially-Robust Deep Q-Network for Algorithmic Trading, MLSS 2025, NCSU.
7. Robust Algorithms for Adversarial Reinforcement Learning, Applied AI Symposium 2024.

♣️ Invited Talks / Seminars

1. Towards Finite-Time Rates for Adversarially-Robust Reinforcement Learning, CORAL Seminar, North Carolina State University.

♥️ Under Preparation/Review