Task Generalization with Deep Reinforcement Learning
The ability to generalize over new tasks is an important research direction in order to build scalable reinforcement learning agents. In this talk, I will discuss how to easily train an agent to generalize to previously unseen tasks in a zero-shot fashion.
Junhyuk Oh is a PhD candidate at the University of Michigan, advised by Professor Honglak Lee and Professor Satinder Singh. His research focuses on deep reinforcement learning problems such as action-conditional prediction, dealing with partial observability, generalization, and planning. His work was featured at MIT Technology Review and Daily Mail. He has served as a co-organizer and a program committee of NIPS deep reinforcement learning symposium and workshop. He also interned at DeepMind and Microsoft Research.