Robotics and Autonomous Systems

By David Silvera-Tawil, David C. Rye, Mari Velonaki. 2014

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Leveraging Human Guidance for Deep Reinforcement Learning Tasks (2019, background): “Most imitation learning or learning from demonstration algorithms assume this type of guidance [Schaal, 1999; Argall et al., 2009; ∗Contact Author Osa et al., 2018].”
Behavioral Cloning from Observation (2018, background): “Enabling this same ability in autonomous agents, referred to as learning from demonstration (LfD), has been given a great deal of attention in the research community [Schaal, 1997; Argall et al., 2009].”
Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary (2017, methodology): “Our approach differs from the work on learning from observation (LfO) in the robotics literature [Argall et al., 2009] in that: (1) LatPlan is trained based on image pairs showing valid before/after images of valid individual actions, while LfO work is largely based on observation (e.”
Reinforcement Learning from Demonstration through Shaping (2015, methodology): “, robotics) previous work focused on using prior knowledge from expert demonstrators to render the learning problem tractable and speed up learning [Argall et al., 2009].”
Imitation Learning from Video by Leveraging Proprioception (2019, methodology): “Imitation learning [Schaal, 1997; Argall et al., 2009; Osa et al., 2018] is a popular method by which artificial agents learn to perform tasks.”
Human Gaze Assisted Artificial Intelligence: A Review (2020, background): “A common approach to achieve this goal is to make machines act like humans, by training machines to recognize and then imitate human teachers’ actions— an approach known as learning from demonstrations (LfD) or imitation learning [Argall et al. , 2009].”