Lecture 4: Imitation from Interventions скачать в хорошем качестве

Lecture 4: Imitation from Interventions

In this fourth lecture, we look at a natural way by which humans teach and learn -- interventions. We show that naively imitating interventions can go horribly wrong. Instead, our key insight is that interventions are laden with implicit information about the human's value function. We take a look at how one may recover the value function from both deterministic and probabilistic paradigms. For more information about me and my work, check out http://www.sanjibanchoudhury.com/ References: 1. Kelly et al. "HG-DAgger: Interactive Imitation Learning with Human Experts" https://arxiv.org/abs/1810.02890 2. Spencer et al. "Learning from Interventions: Human-robot interaction as both explicit and implicit feedback" https://roboticsconference.org/2020/p... 3. Bajcsy et al. "Learning Robot Objectives from Physical Human Interaction" https://proceedings.mlr.press/v78/baj...