Industrial Collaborations
Industry 4.0
Reinforcement learning can play a key role in developing Industry 4.0, acting as an enabler in many central areas such as predictive maintenance, process control, and production. It can be used to analyze data from machines and equipment to identify potential issues before they occur. It can be employed to optimize production processes and increase efficiency, or supply chain and production planning. Overall, reinforcement learning has the potential to improve efficiency, reduce costs, and increase productivity.
Automotive
Reinforcement learning enhances automotive systems by enabling vehicles to learn optimal driving strategies through trial and error. It improves autonomous navigation, adaptive cruise control, and energy management by optimizing long-term safety and efficiency. RL-driven models continuously improve through simulation and real-world data, making transportation smarter and safer.
Finance
Reinforcement learning is reshaping trading by enabling adaptive, data-driven strategies that balance returns and risk aversion. It optimizes portfolio management, algorithmic execution, and market-making by learning from real-time data and uncovering inefficiencies. Unlike static models, RL dynamically adjusts to market shifts, enhancing both profit potential and risk management.
E-commerce
The adoption of machine learning and online learning techniques in e-commerce see a rapid grown during the last years. Dynamic pricing and optimized advertising algorithms are now run by the majority of the platforms in order to increase their revenue. Analytical forecasting tools are adopted to optimize the strategies, analizing the long-term effects of the business choices.
Green Economy
Extreme climatological events are more and more frequent and they have a huge socio-economic impact. CLINT project aims to develop an artificial intelligence framework for the detection, causation and attribution of extreme events (tropical cyclones, heatwaves and warm nights, droughts, and floods). In particular, the main contribution of our group is on the design and application of new Machine Learning techniques or state-of-the-art methods able to process big spatio-temporal climate dataset to gain data-driven information on these events.
Aerospace
Multi-agent reinforcement learning (MARL) empowers aircraft teams to coordinate efficiently by learning optimal strategies for dynamic environments. It enhances autonomy by enabling real-time decision-making, allowing aircraft to adapt to changing conditions without human intervention. By fostering cooperative behavior, MARL improves safety, optimizes flight efficiency, and ensures mission success in aerospace operations.
Startups and Spinoffs
ML Cube
ML cube is a Politecnico di Milano spin-off innovative firm, part of Kayrhos Group, providing cutting-edge solutions for Machine Learning Systems and Life-Cycle-Management Optimization
AD Cube
AD cube is an Artificial Intelligence platform that supports advertisers in the main tasks involved in the optimization of digital marketing campaigns