Projects & Collaboration

We build collaborations around clearly defined technical problems. Our goal is to connect rigorous reinforcement-learning and control methods with platforms, data, and operational needs from academic, public-sector, and industrial partners.

What We Contribute

Algorithm Development

Reinforcement learning, offline RL, robust RL, safe learning, multi-agent learning, and learning-based control.

Theory and Certification

Convergence, finite-time analysis, stability, robustness, Lyapunov methods, and control-theoretic interpretation.

Simulation and Evaluation

Problem formulation, benchmark design, simulation environments, baselines, ablation studies, and quantitative evaluation.

Algorithm Integration

Adaptation to robotics, autonomous driving, industrial processes, energy systems, and computing infrastructure.

Collaboration Areas

• Autonomous-driving perception, reasoning, and control

• Industrial AI, process control, energy, and computing systems

• Reliable reinforcement-learning algorithms and theory

• Multi-agent decision making and coordination

• Vision-language models for sequential decision making

Engagement Models

• Robotics, drones, and autonomous systems

• Joint government-funded research proposals

• Industry-sponsored research and technical validation

• Algorithm development for an existing platform or dataset

• Independent evaluation, benchmarking, and theoretical analysis

Education & Training

We provide lectures, seminars, short courses, and customized training programs in reinforcement learning and signal processing for universities, research institutes, companies, and public organizations.

Courses can cover topics ranging from fundamental concepts to advanced mathematical theory and practical implementation, including deep reinforcement learning, safe and robust learning, digital signal processing, estimation, filtering, and data-driven signal analysis. The content and format can be tailored to the participants’ backgrounds and application needs.

Start a Conversation

For a focused initial discussion, please send a short description of the problem, the available platform or data, the expected outcome, and the intended project structure. 

Email: donghwan@kaist.ac.kr