Sreejeet Maity

Sreejeet Maity

@sreejeetm1729

πŸ›οΈGraduate Research Assistant | Ph.D. Candidate @ North Carolina State University | Interested in Optimization, Reinforcement Learning, and Probability.

North Carolina State University Raleigh, North Carolina
6
Followers
6
Following
26
Public Repos
0
Private Repos

Language Breakdown

Lines of code distribution across 15 owned repositories

3.0M Total LOC
Jupyter Notebook
2,667,699 lines
90.2%
N/A
HTML
165,165 lines
5.6%
N/A
Python
65,905 lines
2.2%
N/A
MATLAB
53,958 lines
1.8%
N/A
Shell
3,145 lines
0.1%
N/A
Other
599 lines
0.0%
N/A
I

I-Shaped Developer

I-shaped

Specialist β€” deep expertise in Jupyter Notebook

Jupyter Notebook
HTML
Python
MATLAB
Shell

Collaboration Network

Global Impact visualization

LIVE
Sreejeet Maity
0 active collaborators

Repos

28

PRs

0

Growth

+18%

Top Collaborators

No collaborator data yet.

Coding Streak

Contribution activity over the past year

13 days
679
Contributions
673
Commits
0
Pull Requests
Jun Jul Aug Sep Oct Nov Dec Jan Feb Mar Apr May Jun
Mo
We
Fr
Based on GitHub activity
Less
More

Top Repositories

Robust_RL_for_Algorithmic_Trading_ECE542

Reinforcement learning (RL) has shown promise in financial applications such as algorithmic trading. However, the high-dimensional nature of market data introduces the curse of dimensionality, making neural network-based function approximators essential. Contributors: Sreejeet Maity, Sai Kavya Marthala, Rajesh Debnath.

3 0
Jupyter Notebook
Robust-Asynchronous-Q-Learning-with-Markovian-Data

Accepted at ICML 2026πŸŽ‰. πšπš˜πš‹πšžπšœπš π™°πšœπš’πš—πšŒ-πš€/π™°πšœπš’πš—πšŒ-πšπ™°πš€/𝙼: The first provably robust variants of asynchronous Q-learning that tolerates adversarially corrupted rewards. Our algorithm is distribution-agnostic, and achieves near-optimal finite-time guarantees up to a provably unavoidable corruptive term.

1 0
Q-Learning-over-Static-and-Time-Varying-Networks

Accepted at ACC 2026 πŸŽ‰. πš…πšπ™³πš€ : We propose and analyze a new algorithm that achieves collaborative speedups in sample complexity for Q-learning over static and time-varying networks.

1 0
Jupyter Notebook
Robust-Q-Learning-under-Corrupted-Rewards

Accepted at IEEE CDC 24 πŸŽ‰. We analyze Q-learning's robustness against strong-contamination attacks that disrupt reward signals. Our robust Q-learning algorithm employs historical data to create resilient Bellman operators, achieving finite-time convergence rates that match existing bounds, with a minor error linked to the corruption fraction.

1 1
Jupyter Notebook
sreejeetm1729

Config files for my GitHub profile.

1 0
sreejeetm1729.github.io

Research Website

0 0
HTML
Federated-MARL-Gym-Environment

π™΅πšŽπšπšŽπš›πšŠπšπšŽπš π™Όπ™°πšπ™»-π™Άπš’πš– : 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 agentsβ€”such as robotsβ€”navigate to accomplish spatially distributed tasks, like reaching delivery points.

0 0
Jupyter Notebook
Robust-Federated-Q-Learning-with-Almost-No-communication

Accepted at ACC 26 πŸŽ‰. πšπš˜πš‹πšžπšœπš π™΅πšŽπš-πš€ : A federated Q-learning algorithm that stays reliable even when a fraction of agents are adversarial. It blends model-based/free updates to ensure (i) high-probability exact convergence in the infinite-sample limit and (ii) near-optimal finite-time rates with collaborative sample-complexity.

0 0
Jupyter Notebook
EconRL

A collection of economics and finance papers that adopt reinforcement learning as a solution method.

0 0
all-rl-algorithms

Implementation of all RL algorithms in a simpler way

0 0
Jupyter Notebook

Open Source Impact

Contributions to external projects

0 merged PRs

No external contributions found.