Duration: 1:11:43

1,830 views

35

Although reinforcement learning (RL) has had many successes, significant amounts of time and/or data can be required to reach acceptable performance. If agents or robots are to be deployed in real world environments, it is critical that our algorithms take advantage of existing human knowledge. This talk will discuss a selection of our recent work that improves RL by leveraging 1) demonstrations and 2) reward feedback from imperfect users.