PhD Candidate • Reinforcement Learning

Decision-making systems for games and real-world control.

I work on deep reinforcement learning, efficient exploration, and evaluation of agents in structured environments.

CV (PDF) Google Scholar GitHub

email@example.com • Berlin, Germany

Research Interests

Focused topics with short, concrete descriptions.

Model-free and model-based RL for sequential decision making.

Policy Optimization Q-learning

Representation learning and function approximation for scalable agents.

PyTorch DQN

Planning, search, and evaluation protocols in board games.

MCTS Evaluation

Short summaries + clear links (demo/code/report).

Q-learning agent trained to play MiniChess with evaluation against baseline opponents.

Python RL Q-learning

Code Report

DQN baseline with replay buffer, target network, and learning curves.

PyTorch Gym DQN

Code Results

Minimal research portfolio template with clean structure and fast deploy.

HTML CSS Responsive

Gallery Code

List papers, preprints, or works in progress.

Manuscripts in preparation. Preprints will be available soon.

For collaboration or a custom academic/technical website.

Email is the fastest way to reach me.

Email me LinkedIn