Reducing trials by thinning-out in skill discovery
Abstract
In this paper, we propose a new concept, thinning-out, for reducing the number of trials in skill discovery. Thinning-out means to skip over such trials that are unlikely to improve discovering results, in the same way as "pruning" in a search tree. We show that our thinningout technique significantly reduces the number of trials. In addition, we apply thinning-out to the discovery of good physical motions by legged robots in a simulation environment. By using thinning-out, our virtual robots can discover sophisticated motions that is much different from the initial motion in a reasonable amount of trials.
References
[1]
Ratle, A.: Accelerating the Convergence of Evolutionary Algorithms by Fitness Landscape Approximation. In: Eiben, A.E., Bäck, T., Schoenauer, M., Schwefel, H-P. (eds.) Proceedings of the Fifth International Conference on Parallel Problem Solving from Nature (PPSN V). LNCS, vol. 1498, pp. 87-96. Springer, Heidelberg (1998).
[2]
Sano, Y., Kita, H., Kamihira, I., Yamaguchi, M.: Online Optimization of an Engine Controller by means of a Genetic Algorithm using History of Search. In: Proceedings of the 3rd Asia-Pacific Conference on Simulated Evolution and Learning (SEAL), pp. 2929-2934 (2000).
[3]
Kim, M.S., Uther, W.: Automatic Gait Optimisation for Quadruped Robots. In: Proceedings of 2003 Australasian Conference on Robotics and Automation, pp. 1-9 (2003).
[4]
Kohl, N., Stone, P.: Machine Learning for Fast Quadrupedal Locomotion. In: The Nineteenth National Conference on Artificial Intelligence (AAAI2004), pp. 611-616 (2004).
[5]
Fidelman, P., Stone, P.: The Chin Pinch: A Case Study in Skill Learning on a Legged Robot. In: Lakemeyer, G., Sklar, E., Sorrenti, D.G., Takahashi, T. (eds.) RoboCup 2006. LNCS (LNAI), vol. 4434, pp. 59-71. Springer, Heidelberg (2007).
[6]
Kobayashi, H., Osaki, T., Williams, E., Ishino, A., Shinohara, A.: Autonomous Learning of Ball Trapping in the Four-legged Robot League. In: Lakemeyer, G., Sklar, E., Sorrenti, D.G., Takahashi, T. (eds.) RoboCup 2006. LNCS (LNAI), vol. 4434, pp. 86-97. Springer, Heidelberg (2007).
[7]
Zagal, J.C., del Solar, J.R.: Learning to Kick the Ball Using Back to Reality. In: Nardi, D., Riedmiller, M., Sammut, C., Santos-Victor, J. (eds.) RoboCup 2004. LNCS (LNAI), vol. 3276, pp. 335-347. Springer, Heidelberg (2005).
[8]
Lee, H., Shen, Y., Yu, C.H., Singh, G., Ng, A.Y.: Quadruped Robot Obstacle Negotiation via Reinforcement Learning. In: Proceedings of the 2006 IEEE International conference on robotics and Automation (ICRA2006) (2006).
[9]
Hiroyasu, T., Miki, M., Sano, M., Shimosaka, H., Tsutsui, S., Dongarra, J.: Distributed Probabilistic Model-Building Genetic Algorithm. In: Cantú-Paz, E., Foster, J.A., Deb, K., Davis, L., Roy, R., O'Reilly, U-M., Beyer, H-G., Kendall, G., Wilson, S.W., Harman, M., Wegener, J., Dasgupta, D., Potter, M.A., Schultz, A., Dowsland, K.A., Jonoska, N., Miller, J., Standish, R.K. (eds.) GECCO 2003. LNCS, vol. 2723, pp. 1015-1028. Springer, Heidelberg (2003).
[10]
Bäck, T.: Evolutionary Algorithms in Theory and Practice. Oxford University Press (1996).
[11]
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998).
[12]
Zaratti, M., Fratarcangeli, M., Iocchi, L.: A 3D Simulator of Multiple Legged Robots based on USARSim. In: Lakemeyer, G., et al. (eds.) RoboCup 2006. LNCS (LNAI), vol. 4434, pp. 13-24. Springer, Heidelberg (2007).
Recommendations
Conflict Discovery and Analysis for Clinical Trials
DH '17: Proceedings of the 2017 International Conference on Digital HealthToday, cancer patients and their caregivers often prefer to share the decision making process with their physicians and may be highly involved in the process of locating and choosing clinical trials for treatment. One issue is that treatments received on ...
Hyperclique pattern discovery
Existing algorithms for mining association patterns often rely on the support-based pruning strategy to prune a combinatorial search space. However, this strategy is not effective for discovering potentially interesting patterns at low levels of ...
Controllability-aware unsupervised skill discovery
ICML'23: Proceedings of the 40th International Conference on Machine LearningOne of the key capabilities of intelligent agents is the ability to discover useful skills without external supervision. However, the current unsupervised skill discovery methods are often limited to acquiring simple, easy-to-learn skills due to the lack ...
Comments
Information & Contributors
Information
Published In
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 01 October 2007
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 1Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 10 Feb 2025