Skip to content
View kundan-kumarr's full-sized avatar

Block or report kundan-kumarr

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
kundan-kumarr/README.md

kundan7kumar

🎓 Ph.D. Candidate | Deep Reinforcement Learning Researcher | AI Engineer

I'm a Ph.D. candidate in Computer Science with a minor in Statistics at Iowa State University, specializing in Deep Reinforcement Learning (DRL) and intelligent control systems. With over 5 years of software engineering experience, I merge academic research with real-world development to create scalable, secure, and high-performance AI systems.


Research & Interests

I'm passionate about pushing the boundaries of AI in complex, dynamic environments. My research explores:

  • Deep Reinforcement Learning for real-time intelligent control
  • Smart Grid Optimization using DRL and physics-informed neural networks
  • Adversarial Robustness in intelligent agents
  • Generative Models and LLMs for decision-making and simulation
  • Autonomous Systems and Cyber-Physical Infrastructure

My work blends statistical modeling, applied machine learning, and simulation-driven development to optimize critical infrastructure and build resilient AI systems.


Technical Toolkit

  • Languages: Python, C++, Java, SQL
  • Frameworks: PyTorch, TensorFlow, Stable Baselines3, Flower AI, OpenAI Gym
  • Simulation & Tools: OpenDSS, SimPy, PowerGym, PyBullet, Docker
  • ML Skills: DRL (PPO, A2C, SAC, DDPG), GNNs, GANs, Bayesian Modeling, Transfer Learning
  • Data Tools: Pandas, NumPy, Scikit-learn, Matplotlib, Seaborn

Projects I'm Proud Of

  • Physics-Informed DRL agents for smart grid volt-var control (IEEE 13/34/123/8500 Node)
  • Federated DRL Framework for decentralized intelligence in cyber-physical systems
  • Adversarial Attack & Defense Models for DRL agents in critical environments
  • LLM-Digital Twin Systems to simulate and reason about power systems

📚 Check out my repositories for clean, documented code and reproducible results.


Interview Preparation guide & Notes

Static Badge


👥 Let’s Collaborate

I'm always open to exciting opportunities in:

  • AI Research
  • Applied Machine Learning
  • Technical Leadership
  • Interdisciplinary Innovation

If you're working on cutting-edge AI, intelligent systems, or want to explore how DRL can change the world—one algorithm at a time, let's talk!


Connect With Me


"The best way to predict the future is to invent it." – Alan Kay
Let's build that future—together.


Snake animation

Pinned Loading

  1. Adversarial-Attacks-Defenses Adversarial-Attacks-Defenses Public

  2. DRL-Research-Hub DRL-Research-Hub Public

  3. Explainable-interpretable-AI Explainable-interpretable-AI Public

  4. Zero2LLM-Crafter Zero2LLM-Crafter Public

    TeX