Reinforcement Learning

After many decades of limited visibility, with a notable exception here and there, reinforcement learning has in recent years come to the foreground of AI, being at the core of unhoped for breakthroughs. Based on the simple principles of trial-and-error, reinforcement learning systems are able to self-learn how to succesfully solve tasks, without the need for a wealth of labeled data. Our lab has been involved in reinforcement learning research since the early 90's, and is currently advancing the state-of-the-art in various segments of the field, including hierarchical reinforcement learning, reward shaping and learning from demonstration, policy gradient, multi-objective reinforcement learning, and many more.