Skip to content
View markub3327's full-sized avatar
🐢
Slowly but surely to the goals.
🐢
Slowly but surely to the goals.

Highlights

  • Pro

Block or report markub3327

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
markub3327/README.md

Martin Kubovčík

🔭 I’m currently working on
Reinforcement Learning frameworks for robotics, Transformer-based models for time-series forecasting, and fun game environments for RL experiments

👯 I’m looking to collaborate on
Reinforcement Learning projects • Robotics with RL • Game AI agents • Transformer applications in real-world problems (HAR, forecasting, etc.)

🤝 I’m looking for help with
Scaling RL experiments to real robotic hardware • Optimizing Transformer models for edge devices • Creating more complex Gymnasium environments

🌱 I’m currently learning
Advanced robotics control with RL • Latest developments in foundation models for sequential decision making • Julia for high-performance scientific computing

💬 Ask me about
Gymnasium environments, Transformers for Human Activity Recognition, Solar Irradiance forecasting, Flappy Bird RL agents, Arduino + Raspberry Pi + ML projects

Fun fact
I created one of the most popular open-source Flappy Bird Gymnasium environments — and yes, I’ve trained agents that are way better at it than I am! 🐦🎮

Preview

Pinned Loading

  1. MarsExplorer MarsExplorer Public

    Forked from dimikout3/MarsExplorer

    MarsExplorer: a Gymnasium environment for deep RL exploration of unknown terrains, featuring procedural terrain generation and PPO benchmarks.

    Python

  2. SB3_Agents SB3_Agents Public

    Reinforcement Learning project training PPO agents on Atari, Retro (Sonic, Mario) or classic environments using Stable Baselines 3, featuring dataset generation and WanDB experiment tracking.

    Python

  3. HAR-Transformer HAR-Transformer Public

    Transformer for Human Activity Recognition

    Jupyter Notebook 77 17

  4. flappy-bird-gymnasium flappy-bird-gymnasium Public

    Forked from Talendar/flappy-bird-gym

    An Gymnasium environment for the Flappy Bird game

    Python 94 32

  5. Solar-Transformer Solar-Transformer Public

    Solar Irradiance Forecasting with Transformer model

    Jupyter Notebook 28 7

  6. AI.EcoSense AI.EcoSense Public

    Automate your garden with machine learning, Arduino and Raspberry Pi.

    C++ 5 1