Synthesising Novel Movements through Latent Space Modulation of Scalable Control Policies

By Sebastian Bitzer, Ioannis Havoutis, Sethu Vijayakumar. 2008

19 citations recorded by the source corpus.

Subfields: Reinforcement Learning, Robotics & Control

How researchers see this paper

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

In Reinforcement Learning

1. George Dimitri Konidaris
2. Bruno Castro da Silva
3. Andrew Barto
4. Sergey Levine
5. Jan Peters
6. Sethu Vijayakumar
7. Philip S. Thomas
8. Pieter Abbeel

In Robotics & Control

1. Sethu Vijayakumar
2. Sebastian Bitzer
3. Andrew Barto
4. George Dimitri Konidaris
5. Bruno Castro da Silva
6. Jan Peters

Citations in the corpus

• Learning Parameterized Skills (2012, background): “Bitzer, Havoutis, and Vijayakumar (2008) synthesize novel movements by modulating DMPs learned in a latent space and projecting them back onto the original pose space.”
• Latent spaces for dynamic movement primitives (2009, methodology): “In earlier work [3] we suggested to use dimensionality reduction (DR) to infer spaces from movement trajectories demonstrated in joint space in which DMP parameters can be related to task variables.”