Learning skills from play: Artificial curiosity on a Katana robot arm

By Hung Quoc Ngo, Matthew D. Luciw, Alexander Förster, J. Urgen Schmidhuber. 2012

38 citations recorded by the source corpus.

Artificial curiosity tries to maximize learning progress. We apply this concept to a physical system. Our Katana robot arm curiously plays with wooden blocks, using vision, reaching, and grasping. It is intrinsically motivated to explore its world. As a by-product, it learns how to place blocks stably, and how to stack blocks.

Subfields: Artificial Intelligence, Computer Science Applications, Control and Systems Engineering

How researchers see this paper

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

In Artificial Intelligence

In Computer Science Applications

In Control and Systems Engineering

Citations in the corpus

Learning by Playing - Solving Sparse Reward Tasks from Scratch (2018, methodology): “…Reinforcement Learning with the help of so called “intrinsic motivation” rewards (Chentanez et al., 2005; Singh et al., 2009) has, furthermore, been studied for controlling real robots by Ngo et al. (2012) and combined with Deep RL techniques by Kulkarni et al. (2016a); Dilokthanakul et al. (2017).”
Some Considerations on Learning to Explore via Meta-Reinforcement Learning (2018, background): “As a result of these shortcomings, a variety of new approaches to exploration in deep RL have recently been suggested [34, 9, 31, 18, 4, 19, 17, 8, 23, 17, 8, 26, 25, 32, 33, 12, 24].”
Curiosity driven reinforcement learning for motion planning on humanoids (2014, methodology): “Model-based RL with curiosity-driven exploration has been implemented on a Katana manipulator (Ngo et al., 2012), such that the agent learns to build a tower, without explicitly rewarding any kind of stacking.”