International Conference on Intelligent Robots and Systems Robot Behavior Adaptation for Human-Robot Interaction based on Policy Gradient Reinforcement Learning *

How researchers see this paper

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

Reinforcement learning in robotics: A survey (2013, background): “…learned to adjust the existing behaviors of a lower-level controller, such as when choosing among different robot– human interaction possibilities (Mitsunaga et al., 2005), selecting among different striking movements in a table tennis task (Peters et al., 2010a), and setting the meta-actions…”
Reinforcement learning of motor skills with policy gradients (2008, methodology): “Due to the simplicity of this approach, finite-difference methods have been successfully applied to robot motor skill learning in numerous applications (Kohl & Stone, 2004; Mitsunaga et al., 2005; Miyamoto et al., 1995, 1996; Tedrake et al., 2005).”
Influences on proxemic behaviors in human-robot interaction (2009, background): “Similar research is currently being done on how end-users might teach robots to engage in acceptable proxemic behaviors [13].”