Christopher Towell MRes

Christopher Towell

  Learning Nullspace Policies
Towell, C, Howard, M & Vijayakumar, S 2010, Learning Nullspace Policies. in IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010). IEEE, NEW YORK, pp. -, IEEE/RSJ International Conference on Intelligent Robots and Systems, Taipei, 18/10/10.

Many everyday tasks performed by people, such as reaching, pointing or drawing, resolve redundant degrees of freedom in the arm in a similar way. In this paper we present a novel method for learning the strategy used to resolve redundancy by exploiting the variability in multiple observations of different tasks. We demonstrate the effectiveness of this method on three simulated plants: a toy example, a three link planar arm, and the KUKA lightweight arm.

General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Towell, Christopher, Howard, Matthew & Vijayakumar, Sethu.
Number of pages: 8
Pages: -
Publication Date: 2010
Publication Information
Category: Conference contribution
Original Language: English
  Geodesic Gaussian kernels for value function approximation
Sugiyama, M, Hachiya, H, Towell, C & Vijayakumar, S 2008, 'Geodesic Gaussian kernels for value function approximation' Autonomous Robots, vol 25, no. 3, pp. 287-304. DOI: 10.1007/s10514-008-9095-6
The least-squares policy iteration approach works efficiently in value function approximation, given appropriate basis functions. Because of its smoothness, the Gaussian kernel is a popular and useful choice as a basis function. However, it does not allow for discontinuity which typically arises in real-world reinforcement learning tasks. In this paper, we propose a new basis function based on geodesic Gaussian kernels, which exploits the non-linear manifold structure induced by the Markov decision processes. The usefulness of the proposed method is successfully demonstrated in simulated robot arm control and Khepera robot navigation.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: Sugiyama, Masashi, Hachiya, Hirotaka, Towell, Christopher & Vijayakumar, Sethu.
Keywords: (Reinforcement learning, Value function approximation, Markov decision process, Least-squares policy iteration, Gaussian kernel, , , . )
Number of pages: 18
Pages: 287-304
Publication Date: 2008
Publication Information
Category: Article
Journal: Autonomous Robots
Volume: 25
Issue number: 3
Original Language: English