Reinforcement Learning
Research Lab @ UniPD
RL2 is a research group part of the Department of Information Engineering from the University of Padova
Who we are
Our research group specializes in cutting-edge Deep Reinforcement Learning across diverse domains. In smart mobility, we engineer RL algorithms for optimizing traffic flow, ride-sharing systems, and autonomous vehicle decision-making. In robotics, we focus on RL applications for robotic manipulation, navigation, and task automation. Exploring semiconductor manufacturing, we leverage RL for process optimization. Our work extends to refining RL algorithms, including hierarchical and abstract methods, enhancing learning efficiency and scalability. Through interdisciplinary collaboration, we strive to push the boundaries of RL, creating adaptive, intelligent systems with real-world impact.
Collaborations
Foster interdisciplinary cooperation to tackle challenging RL problems collectively.
Collaborations
Foster interdisciplinary cooperation to tackle challenging RL problems collectively.
Collaborations
Foster interdisciplinary cooperation to tackle challenging RL problems collectively.
Research Threads
RL2 is a research group that focuses on Reinforcement Learning and its applications in several domains, publishing several papers for each of them.
1. Smart Mobility
Researching reinforcement learning techniques to enhance traffic control in urban environments, aiming for efficient, adaptive strategies that optimize traffic flow, reduce congestion, and improve overall mobility in smart cities and transportation networks.
Learn more2. Manufacturing
Applying reinforcement learning to semiconductor manufacturing for optimized machine lot scheduling, improving production efficiency and reducing bottlenecks in complex fabrication processes.
Learn more3. Robotic Manipulation
Utilizing reinforcement learning in robotic manipulation to optimize actuator control, enhancing robotic dexterity and adaptability in complex tasks involving grasping, manipulation, and assembly.
Learn more4. Algorithms
Researching reinforcement learning algorithms tailored for continuous control in robotics, alongside abstract, explainable, and hierarchical RL frameworks.
Learn more5. Telecommunication
Applied reinforcement learning optimizes telecommunication systems through adaptive protocols, network management, and resource allocation for efficient and self-learning communication infrastructure.
Learn more6. HVAC&R
Applied reinforcement learning optimizes HVAC and refrigeration systems through adaptive control strategies, energy management, and equipment operation for efficient and self-learning building environments.
Learn more