Publications

Journal Papers

  1. S. Elfwing, E. Uchibe, K. Doya, and H. I. Christensen. Evolutionary Development of Hierarchical Learning Structures. IEEE Transactions on Evolutionary Computations, Vol. 11, Issue 2, pages 249--264, 2007.
    [IEEE Xplore] [download]
  2. T. Sato, E. Uchibe, and K. Doya. Learning how, what, and whether to communicate: emergence of protocommunication in reinforcement learning agents. Journal of Artificial Life and Robotics, vol. 12, 2007.
  3. E. Uchibe and M. Asada. Incremental coevolution with competitive and cooperative tasks in a multi-robot environment. Proceedings of the IEEE, Vol. 94, Issue 7, pages 1412--1424, 2006.
    [IEEE Xplore]
  4. K. Doya and E. Uchibe. The Cyber Rodent Project: Exploration of Adaptive Mechanisms for Self-Preservation and Self-Reproduction. Adaptive Behavior, vol. 13, no. 2, pages 149--160, 2005.
    [download]
  5. G. Capi and K. Doya. Evolution of neural architecture fitting environmental dynamics. Adaptive Behavior, vol. 13, no. 1, pages 53--66, 2005.
    [download]

Reviewed Conference Papers

  1. T. Morimura, E. Uchibe, and K. Doya. Natural Actor-Critic with Baseline Adjustment for Variance Reduction. In Proc. of the 13th International Symposium on Artificial Life and Robotics (AROB2007), 2008.
    [download]
  2. E. Uchibe and K. Doya. Finding Exploratory Rewards by Embodied Evolution and Constrained Reinforcement Learning in the Cyber Rodents. In Proc. of the 14th International Conference on Neural Information Processing, 2007 (oral presentation).
    One of the Five Best Paper Awards.
    [download (provisional proceeding version)]
  3. E. Uchibe and K. Doya. Constrained reinforcement learning from intrinsic and extrinsic rewards. In Proc. of the IEEE International Conference on Development and Learning, 2007 (oral presentation).
    [download]
  4. T. Sato, E. Uchibe, and K. Doya. Learning how, what, and whether to communicate: emergence of protocommunication in reinforcement learning agents. In Proc. of the 12th International Symposium on Artificial Life and Robotics (AROB2007), 2007.
  5. E. Brunskill, E. Uchibe, and K. Doya. Learning Adaptive Sensory Observation-Action Policies for Mobile Robot Control. In Proc. of the IEEE International Conference on Robotics and Automation, Poster presentation, 2006.
    [download]
  6. T. Morimura, E. Uchibe, and K. Doya. Utilizing the natural gradient in temporal difference reinforcement learning with eligibility traces. In Proc. of the 2nd International Symposium on Information Geometry and its Application, pages 256--263, 2005.
    [download]
  7. S. Elfwing, E. Uchibe, K. Doya, and H. I. Christensen. Biologically Inspired Embodied Evolution of Survival. In Proc. of the IEEE Congress on Evolutionary Computation, 2005.
    [download]
  8. E. Uchibe and K. Doya. Reinforcement learning with multiple heterogeneous modules: A framework for developmental robot learning. In Proc. of the 4th International Conference on Development and Learning, 2005.
    [download]
  9. S. Elfwing, E. Uchibe, K. Doya, and H. I. Christensen. Multi-Agent Reinforcement Learning: Using Macro Actions to Learn a Mating Task, In Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2004.
    [download]
  10. E. Uchibe, and K. Doya. Competitive-Cooperative-Concurrent Reinforcement Learning with Importance Sampling, In Proc. of International Conference on Simulation of Adaptive Behavior: From Animals and Animats, pages 287--296, 2004.
    Best Philosophical Paper Award (Sponsored by Applied AI Systems).
    [download]
  11. G. Capi, and K. Doya. Evolving recurrent neural controllers for sequential tasks - a parallel implementation. In Proc. of Congress on Evolutionary Computation, 1, 514-519, 2003.
  12. A. Eriksson, G. Capi, and K. Doya. Evolution of Meta-parameters in Reinforcement Learning Algorithm. In Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems, 2003.
    [download]
  13. S. Elfwing, E. Uchibe, and K. Doya. An Evolutionary Approach to Automatic Construction of the Structure in Hierarchical Reinforcement Learning. In Proc. of the Genetic and Evolutionary Computaion Conference, 2003.
    [download]
  14. G. Capi, E. Uchibe, and K. Doya. Selection of Neural Architecture and the Environment Complexity. In Proc. of the 3rd International Symposium on Human and Artificial Intelligent Systems. 2002.
    [download]

Conference Papers (without review)

Technical Report

  1. T. Morimura, E. Uchibe, J. Yoshimoto, and K. Doya. Policy Gradient Reinforcement Learning with Log Stationary Distribution Gradients. NAIST Technical Report, NAIST-IS-TR-2007013, 2007.
    [download from NAIST]

Ph.D. Thesis

  1. Stefan Elfwing. Embodied Evolution of Learning Ability. KTH School of Computer Science and Communication, Sweden, 2007.
    [download from KTH Biblioteket]
    [download from this server]

Master's Thesis

  1. Anders Eriksson. Evolution of Meta-parameters in Reinforcement Learning. Master's Thesis in Computer Science at the School of Computer Science and Engineering, Royal Institute of Technology, 2003.
    [download]
  2. Stefan Elfwing. An Evolutionary Approach to Automatic Construction of the Structure in Hierarchical Reinforcement Learning. Master's Thesis in Computer Science at the School of Computer Science and Engineering, Royal Institute of Technology, 2003.
    [download]