Self-reflective deep reinforcement learning

Article English OPEN
Altahhan, A;
  • Publisher: IEEE

© 2016 IEEE. In this paper we present a new concept of self-reflection learning to support a deep reinforcement learning model. The self-reflective process occurs offline between episodes to help the agent to learn to navigate towards a goal location and boost its onlin... View more
  • References (22)
    22 references, page 1 of 3

    [1] A. Vardy and R. Moller, “Biologically plausible visual homing methods based on optical flow techniques”, Connection Science, vol. 17, pp. 47- 89, 2005.

    [2] N. Tomatis et al, “Combining Topological and Metric: a Natural Integration for Simultaneous Localization and Map Building”, presented at Proc. Of the Fourth European Workshop on Advanced Mobile Robots (Eurobot), 2001.

    [3] Jochen Zeil, “Visual homing: an insect perspective, Current Opinion in Neurobiology”, Volume 22, Issue 2, pp. 285-293, ISSN 0959-4388, April 2012

    [4] R. S. Sutton and A. Barto, “Reinforcement Learning, an introduction”, Cambridge, Massachusetts: MIT Press, 1998.

    [5] V. Konda and J. Tsitsiklis, “Actor-Critic algorithms”, presented at NIPS 12, 2000.

    [6] O. Ziv and N. Shimkin, “Multigrid Methods for Policy Evaluation and Reinforcement Learning”, presented at IEEE International Symposium on Intelligent Control, Limassol, 2005.

    [7] C. Zhang at al, “Efficient multi-agent reinforcement learning through automated supervision”, presented at International Conference on Autonomous Agents Estoril, Portugal, 2008.

    [8] S. Bhatnagar et al, “Incremental Natural Actor-Critic Algorithms”, presented at Neural Information Processing Systems (NIPS19), 2007.

    [9] G. Hinton et al, “A fast learning algorithm for deep belief nets”. Neural Computation,18(7):1527-1554, 2006.

    [10] A. Coates et al, “An Analysis of Single-Layer Networks in Unsupervised Feature Learning”, in AISTATS 14, 2011.

  • Metrics
Share - Bookmark