Skip to main content
Have a personal or library account? Click to login
Combining Local and Global Direct Derivative-Free Optimization for Reinforcement Learning Cover

Combining Local and Global Direct Derivative-Free Optimization for Reinforcement Learning

Cybernetics and Information Technologies
Volume 12 (2012): Issue 3 (September 2012)
By: ,   and    
Open Access
|Mar 2013
References

References

  1. 1. Barash, D.. A genetic search in policy space for solving Markov decision processes, - In: AAAI Spring Symposium on Search Techniques for Problem Solving under Uncertainty and Incomplete Information, 1999.
    Search in Google Scholar
  2. 2. Baxter, J., P. Bartlett. Direct gradient-based reinforcement learning, - In: Proceedings of IEEE International Symposium on Circuits and Systems, Vol. 3, IEEE, 2000, 271-274.
    Search in Google Scholar
  3. 3. Brachetti, P., M. De Felice Ciccoli, G. Di Pillo, S. Lucidi. A new version of the Price’s algorithm for global optimization, Journal of Global Optimization, Vol. 10, No 2, 1997, 165-184.
    Open DOISearch in Google Scholar
  4. 4. Carpin, S., M. Lewis, J. Wang, S. Balakirsky, C. Scrapper. Bridging the gap between simulation and reality in urban search and rescue, Robocup 2006: Robot Soccer World Cup X, 1-12.
    Open DOISearch in Google Scholar
  5. 5. Conn, A., K. Scheinberg, L. Vicente. Introduction to derivative-free optimization, Vol. 8, Society for Industrial Mathematics, 2009.
    Open DOISearch in Google Scholar
  6. 6. Dorigo, M., M. Birattari, T. Stutzle. Ant colony optimization, IEEE Computational Intelligence Magazine, Vol. 1, No 4, 2006, 28-39.
    Open DOISearch in Google Scholar
  7. 7. Glover, F., M. Laguna. Tabu search, Vol. 1, Springer, 1998.
    Open DOISearch in Google Scholar
  8. 8. Goldberg, D.. Genetic algorithms in search, optimization, and machine learning, Addisonwesley, 1989.
    Search in Google Scholar
  9. 9. Gomez, F., J. Schmidhuber, R. Miikkulainen. Efficient Non-Linear Control through Neuroevolution, - In: Proceedings of the European Conference on Machine Learning, Springer, Berlin, 2006, 654-662.
    Open DOISearch in Google Scholar
  10. 10. Horst, R., P. Pardalos, N. Thoai. Introduction to global optimization, Springer, 2000.
    Open DOISearch in Google Scholar
  11. 11. Jakobi, N., P. Husbands, I. Harvey. Noise and the reality gap: The use of simulation in evolutionary robotics, Advances in artificial life, 704-720.
    Open DOISearch in Google Scholar
  12. 12. Kakade, S.. A natural policy gradient, Advances in neural information processing systems, Vol. 14, 2001, 1531-1538.
    Search in Google Scholar
  13. 13. Kirkpatrick, S., C. Gelatt Jr, M. Vecchi. Optimization by simulated annealing, Science, Vol. 220, No 4598, 1983, 671-680.
    Open DOISearch in Google Scholar
  14. 14. Kober, J., J. Peters. Policy search for motor primitives in robotics, Machine learning, Vol. 84, No 1, 2011, 171-203.
    Open DOISearch in Google Scholar
  15. 15. Kormushev, P., D. G. Caldwell. Simultaneous Discovery of Multiple Alternative Optimal Policies by Reinforcement Learning, - In: IEEE International Conference on Intelligent Systems (IS 2012), 2012.
    Open DOISearch in Google Scholar
  16. 16. Lucidi, S., M. Sciandrone. On the global convergence of derivative-free methods for unconstrained optimization, SIAM Journal of Optimization, Vol. 13, No 1, 2002, 97-116.
    Open DOISearch in Google Scholar
  17. 17. Peters, J., S. Schaal. Policy gradient methods for robotics, - In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, 2006, 2219-2225.
    Open DOISearch in Google Scholar
  18. 18. Peters, J., S. Schaal. Reinforcement learning by reward-weighted regression for operational space control, - In: Proceedings of the 24th international conference on Machine learning, ACM, 2007, 745-750.
    Open DOISearch in Google Scholar
  19. 19. Peters, J., S. Vijayakumar, S. Schaal. Natural Actor-Critic, - In: Proceedings of the 16th European Conference on Machine Learning (ECML), 2005, 280-291.
    Open DOISearch in Google Scholar
  20. 20. Price, W.. Global optimization by controlled random search, Journal of Optimization Theory and Applications, Vol. 40, No 3, 1983, 333-348.
    Open DOISearch in Google Scholar
  21. 21. Ribas, D., N. Palomeras, P. Ridao, M. Carreras, A. Mallios. Girona 500 AUV, from survey to intervention, IEEE/ASME Transactions on Mechatronics, Vol. 17, No 1, 2012, 46-53.
    Open DOISearch in Google Scholar
  22. 22. Sutton, R., D. McAllester, S. Singh, Y. Mansour. Policy gradient methods for reinforcement learning with function approximation, Advances in neural information processing systems, Vol. 12, No 22.
    Search in Google Scholar
  23. 23. Theodorou, E., J. Buchli, S. Schaal. A generalized path integral control approach to reinforcement learning, The Journal of Machine Learning Research, Vol. 9999, 2010, 3137-3181.
    Search in Google Scholar
  24. 24. Torczon, V., et al .. On the convergence of pattern search algorithms, SIAM Journal on optimization, Vol. 7, No 1, 1997, 1-25.
    Open DOISearch in Google Scholar
  25. 25. Torn, A., A. Zilinska s. Global Optimization, Springer, 1989.
    Search in Google Scholar
  26. 26. Williams, R.. Simple statistical gradient-following algorithms for connectionist reinforcement learning, Machine learning, Vol. 8, No 3, 1992, 229-256.
    Open DOISearch in Google Scholar
DOI: https://doi.org/10.2478/cait-2012-0021 | Journal eISSN: 1314-4081 | Journal ISSN: 1311-9702 (formerly 1314-4081)
Journal RSS Feed
Language: English
Page range: 53 - 65
Published on: Mar 22, 2013
Published by: Bulgarian Academy of Sciences, Institute of Information and Communication Technologies
In partnership with: Paradigm Publishing Services
Keywords:
Reinforcement learning,
policy search,
derivative-free optimization,
robotics,
autonomous underwater vehicles
Related subjects:
Computer sciences,
Information technology

© 2013 Matteo Leonetti, Petar Kormushev, Simone Sagratella, published by Bulgarian Academy of Sciences, Institute of Information and Communication Technologies
This work is licensed under the Creative Commons License.

Volume 12 (2012): Issue 3 (September 2012)
Previous article
Next article