Legs that can walk: Embodiment-Based Modular Reinforcement Learning applied
Jacob, D., Polani, D. and Nehaniv, C.L.
(2005)
Legs that can walk: Embodiment-Based Modular Reinforcement Learning applied.
In:
Procs 2005 IEEE Int Symposium on Computational Intelligence in Robotics and Automation : CIRA 2005.
Institute of Electrical and Electronics Engineers (IEEE), FIN, pp. 365-372.
ISBN 0-7803-9355-4
Experiments to illustrate a novel methodology for reinforcement learning in embodied physical agents are described. A simulated legged robot is decomposed into structurebased modules following the authors' EMBER principles of local sensing, action and learning. The legs are individually trained to 'walk' in isolation, and re-attached to the robot; walking is then sufficiently stable that learning in situ can continue. The experiments demonstrate the benefits of the modular decomposition: state-space factorisation leads to faster learning, in this case to the extent that an otherwise intractable problem becomes learnable.
Item Type | Book Section |
---|---|
Date Deposited | 15 May 2025 16:24 |
Last Modified | 30 May 2025 23:11 |
Explore Further
-
picture_as_pdf - 101964.pdf
-
subject - Published Version
Share this file
Downloads