Copyright and Licensing
Articles accepted for publication will be licensed under the Creative Commons BY-NC-SA. Authors must sign a non-exclusive distribution agreement after article acceptance.
Improved automatic discovery of subgoals for options in hierarchical
Keywords:
subgoal discovery, reinforcement learning, optionsAbstract
Options have been shown to be a key step in extending reinforcement learning beyond low-level reactionary systems to higher-level, planning systems. Most of the options research involves hand-crafted options; there has been only very limited work in the automated discovery of options. We extend early work in automated option discovery with a flexible and robust method.
Downloads
Download data is not yet available.
References
[1] L. J. Lin. Self-improving reactive agents based on reinforcement learning, planning and teaching. Mag chine Learning, 8:293–321, 1992.
[2] O. Maron and T. Lozano-Perez. A framework for multiple-instance learning. In Advances in Neural Information Processing Systems, NIPS 98, pages 570–576, 1998.
[3] A. McGovern and A. G. Barto. Accelerating reinforcement learning through the discovery of useful subgoals. In Proceedings ofteh 6th International Symposium on Artificial Intelligence, Robotics and Automation in Space: i-SAIRAS 2001, 2001.
[4] A. McGovern and A. G. Barto. Automatic discovery of subgoals in reinforcement learning using diverse density. In Proceedings of the Eighteenth International Conference on Machine Learning, pages h 361–368, Williams College, MA., 2001.
[5] A. McGovern and A. G. Barto. Linear discriminant diverse density for automatic discovery of subgoals in reinforcement learning. In Workshop on Hierarchy and Memory in Reinforcement Learning, ICML 2001, Williams College, MA, 2001.
[6] R. S. Sutton and D. Precup. Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence, 112:181–211, 1999.
[7] Richard S. Sutton and Andrew G. Barto. Reinforcement Learning: An Introduction. The MIT Press, 1998.
[2] O. Maron and T. Lozano-Perez. A framework for multiple-instance learning. In Advances in Neural Information Processing Systems, NIPS 98, pages 570–576, 1998.
[3] A. McGovern and A. G. Barto. Accelerating reinforcement learning through the discovery of useful subgoals. In Proceedings ofteh 6th International Symposium on Artificial Intelligence, Robotics and Automation in Space: i-SAIRAS 2001, 2001.
[4] A. McGovern and A. G. Barto. Automatic discovery of subgoals in reinforcement learning using diverse density. In Proceedings of the Eighteenth International Conference on Machine Learning, pages h 361–368, Williams College, MA., 2001.
[5] A. McGovern and A. G. Barto. Linear discriminant diverse density for automatic discovery of subgoals in reinforcement learning. In Workshop on Hierarchy and Memory in Reinforcement Learning, ICML 2001, Williams College, MA, 2001.
[6] R. S. Sutton and D. Precup. Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence, 112:181–211, 1999.
[7] Richard S. Sutton and Andrew G. Barto. Reinforcement Learning: An Introduction. The MIT Press, 1998.
Downloads
Published
2003-10-01
Issue
Section
Original Articles
License
How to Cite
[1]
“Improved automatic discovery of subgoals for options in hierarchical”, JCS&T, vol. 3, no. 02, pp. p. 9–14, Oct. 2003, Accessed: Mar. 08, 2026. [Online]. Available: https://journal.info.unlp.edu.ar/JCST/article/view/932
