THE Markov Decision Problem (MDP) is the basis of a very important area of Artificial Intelligence (AI) called Reinforcement Learning (RL). This learning technique has been used in many AI problems, such as creating intelligent agents for games, robotics, autonomous vehicles, and finance. This seminar has the main objective of presenting the MDP and RL, along with the main applications in the real world.

• Moderation and coordination: Luciana Barbosa; Sandra Ribeiro;
• Speaker: Alberto Sardinha;
• Date: June 22 (Tuesday) at 18:30;
• Conference via Zoom – ID: 830 5467 4599
• Keyword: 383744