Reinforcement learning of hierarchical skills on the sony aibo robot

By Vishal Soni, Satinder Singh. 2005

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. Sergey Levine
2. Pieter Abbeel
3. Jan Peters
4. Gerhard Neumann
5. George Dimitri Konidaris
6. Chelsea Finn
7. Christian Daniel
8. Herke Van Hoof

In Robotics & Control

1. Jan Peters
2. Gerhard Neumann
3. Sergey Levine
4. J. Bagnell
5. George Dimitri Konidaris
6. Andrew Barto
7. Christian Daniel
8. Oliver Kroemer

Citations in the corpus

• Learning Parameterized Skills (2012, background): “Soni and Singh (2006) create options whose termination criteria can be adapted on-the-fly to deal with changing aspects of a task.”
• Reinforcement learning in robotics: A survey (2013, background): “A task of transporting a ball with a dog robot (Soni and Singh, 2006) can be learned with semi-automatically discovered options.”
• Autonomous Skill Acquisition on a Mobile Manipulator (2011, background): “Soni and Singh (2006) focused on learning and using macro-actions with pre-designated salient events as subgoals on a Sony Aibo robot.”
• Towards learning hierarchical skills for multi-phase manipulation tasks (2015, background): “Hiearchical reinforcement learning methods learn both a library of skills as well as a high-level policy for sequencing them [37], [13], [20], [34], [15].”