Currently strengthening my foundations in PyTorch and Deep Reinforcement Learning, while exploring autonomous navigation, ROS 2, and simulation-based robotics.
- 🧠 Interested in: Deep Reinforcement Learning, autonomous robotics and intelligent control
- 🤖 Exploring: DQN, TurtleBot3, ROS 2, Gazebo, GenAI, MLops, NLP
- ⚡ Background: EEE, electronics,Machine Learning, PLC automation, and embedded systems
- 🌱 Current goal: turn working implementations into well-tested, reproducible projects
|
Ongoing learning and development project exploring DQN-based mobile robot navigation with ROS 2 and Gazebo. 
|
Learning Deep Q-Networks with PyTorch, experience replay, target networks, and epsilon-greedy exploration in Gymnasium. 
|
|
Ultrasonic proximity detector using a 555 timer IC, LED, buzzer, resistors, capacitors, and a battery—without a programmable microcontroller. 
|
Hands-on learning with Siemens PLCs, TIA Portal, PLC simulation, and basic automation logic. 
|
Note: If your FrozenLake repository has a different name or is not public yet, update that link before publishing.
🧪 Currently Working On
| Area | Focus |
|---|---|
| 🧠 Deep Reinforcement Learning | Understanding DQN, training stability, replay memory, and evaluation. |
| 🤖 Robotics | Building a ROS 2 + Gazebo workflow for TurtleBot3 navigation. |
| 📈 Research skills | Learning to design fair comparisons, analyze results, and document limitations. |
🤝 Let's Build Something I'm always interested in learning from people working on robotics, reinforcement learning, electronics, and intelligent control systems.
