Reinforcement Learning algorithms

Reinforcement learning (RL) is a branch of machine learning where an agent learns to make decisions by interacting with an environment to maximize cumulative rewards. It mimics how humans and animals learn through trial and error. In RL, the agent receives feedback in the form of rewards or penalties based on its actions, enabling it to learn optimal strategies over time. This approach is widely applied in robotics, gaming, finance, and more. Our research group specializes in advancing RL algorithms, focusing on deep reinforcement learning and its applications. Explore our publications to delve into cutting-edge developments and insights in this exciting field.

Our latest publications in this research area

2024

• Sinigaglia, A., Turcato, N., Libera, A. D., Carli, R., & Susto, G. A. (2024). Exploiting Estimation Bias in Deep Double Q-Learning for Actor-Critic Methods.
• Wiebe, F., Turcato, N., Dalla Libera, A., Zhang, C., Vincent, T., Vyas, S., ... & Kumar, S. (2024). Reinforcement learning for athletic intelligence: Lessons from the 1st “ai olympics with realaigym” competition,”. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24, K. Larson, Ed. International Joint Conferences on Artificial Intelligence Organization (Vol. 8, pp. 8833-8837).
• Turcato, N., Libera, A. D., Giacomuzzo, G., Carli, R., & Romeres, D. (2024). Learning control of underactuated double pendulum with Model-Based Reinforcement Learning. arXiv preprint arXiv:2409.05811.
• Calì, M., Sinigaglia, A., Turcato, N., Carli, R., & Susto, G. A. (2024). AI Olympics challenge with Evolutionary Soft Actor Critic. arXiv preprint arXiv:2409.01104.

2023

• Marcato, D., Bellan, L., Bortolato, D., Comunian, M., Galatà, A., Gelain, F., ... & Susto, G. A. (2023). Demonstration of Beam Emittance Optimization using Reinforcement Learning. In Proceedings of the 14th International Particle Accelerator Conference.

2022

• Calvi, G., Manzoni, E., Rampazzo, M. (2022). Reinforcement Q-learning for Closed-loop Hypnosis Depth Control in Anesthesia. In 2022 30th Mediterranean Conference on Control and Automation (MED) (pp. 164-169). IEEE.

2020

• Maggipinto, M., Susto, G. A., & Chaudhari, P. Proximal deterministic policy gradient. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 5438-5444). IEEE.