We focus our research on intelligent, autonomous systems and agents. In TRAIL, we regard the term intelligence with respect to the behaviour of an entity. For simplification we assume an entity to be intelligent if it is able to learn from past experience, to think about future events or actions, and to act according to its knowledge, thoughts, and interaction with other entities. Our research in TRAIL focuses on these three main aspects:
Learn
Learning is the process of extracting knowledge from data which represents past experience. The knowledge can be used to identify salient patterns or structures in data or to make predictions. Machine Learning is currently the most active field in AI and has achieved tremendous progress in various domains over the last decade.
Think
The goal of Thinking is to solve problems via explicit reasoning given a problem model, rules, or a simulator. Planning and Scheduling represent common classes of problem solvers and are often used for complex tasks like routing, task allocation, and decision making.
Act
Acting of AI systems involves the process of making intelligent decisions based on knowledge learned from prior experience or explicit reasoning. Acting is also influenced by coexisting AI systems e.g., in a multi-agent system. Social interaction with humans is important to integrate AI into our everyday life
CROP
Towards Distributional-Shift Robust Reinforcement Learning using Compact Reshaped Observation Processing
DIRECT
Learning from Sparse and Shifting Rewards using Discriminative Reward Co-Training
Social Neural Network Soups with Surprise Minimization
What happens when concepts from artificial chemistry and neural networks intersect? They become social (or try to).