The seminar will be held on Monday 4. 3. 2024 at 14:00 in the AS-meeting room 474, the speaker will be Marko Ruman.

Deep reinforcement learning has shown an ability to achieve super-human performance in solving complex reinforcement learning tasks only from raw-pixels. However, it fails to reuse knowledge from previously learnt tasks to solve new, unseen ones. To generalize and reuse knowledge is one of the fundamental requirements for creating a truly intelligent agent. In this seminar, I’ll discuss my ongoing work on N-to-1 knowledge transfer, where an agent leverages insights from N previously solved tasks to tackle new challenges.