Algorithm for Base Action Set Generation Focusing on Undiscovered Sensor Values
Source abstract
Abstract
Previous machine learning algorithms use a given base action set designed by hand or enable locomotion for a complicated task through trial and error processes with a sophisticated reward function. These generated actions are designed for a specific task, which makes it difficult to apply them to other tasks. This paper proposes an algorithm to obtain a base action set that does not depend on specific tasks and that is usable universally. The proposed algorithm enables as much interoperability among multiple tasks and machine learning methods as possible. A base action set that effectively changes the external environment was chosen as a candidate. The algorithm obtains this base action set on the basis of the hypothesis that an action to effectively change the external environment can be found by observing events to find undiscovered sensor values. The process of obtaining a base action set was validated through a simulation experiment with a differential wheeled robot.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Reinforcement Learning in Robotics · Robot Manipulation and Learning · Evolutionary Algorithms and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science, Kitami Institute of Technology, 165 Koencho, Kitami, Hokkaido 090-8507, Japan
Department of Complex and Intelligent Systems, Future university hakodate, 116-2, Kameda-Nakanocho, Hakodate 041-8655, Japan
References (27)
Show source-provided references
1. Developmental robotics: A survey10.1080/09540090310001655110 ↗
2. Reinforcement learning: A survey10.1613/jair.301 ↗
3. Scheier, C., and Pfeifer, R. (1995, January 4–6). Classification as sensory-motor coordination. Proceedings of the Third European Conference on Artificial Life, Granada, Spain.10.1007/3-540-59496-5_333 ↗
4. Zhu, Y., Mottaghi, R., Kolve, E., Lim, J.J., Gupta, A., Li, F.F., and Farhadi, A. (June, January 29). Target-driven visual navigation in indoor scenes using deep reinforcement learning. Proceedings of the 2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore.10.1109/ICRA.2017.7989381 ↗
5. Qureshi, A.H., Nakamura, Y., Yoshikawa, Y., and Ishiguro, H. (2016, January 15–17). Robot gains social intelligence through multimodal deep reinforcement learning. Proceedings of the 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids), Cancun, Mexico.10.1109/HUMANOIDS.2016.7803357 ↗
6. Lei, T., and Ming, L. (2016, January 6–10). A robot exploration strategy based on q-learning network. Proceedings of the IEEE International Conference on Real-time Computing and Robotics (RCAR), Angkor Wat, Cambodia.
7. Reinforcement learning for robot soccer10.1007/s10514-009-9120-4 ↗
8. Reinforcement Learning in the Multi-robot Domain10.1023/A:1008819414322 ↗
9. Sutton, R.S., Barto, A.G., Barto, A.G., and Bach, F. (1998). Reinforcement Learning: An Introduction, MIT Press.10.1109/TNN.1998.712192 ↗
10. Mitchell, T.M., and Thrun, S.B. (December, January 30). Explanation-based neural network learning for robot control. Proceedings of the 5th International Conference on Neural Information Processing Systems, Denver, CO, USA.
11. Reward-modulated hebbian learning of decision making10.1162/neco.2010.03-09-980 ↗
12. Hafner, R., and Riedmiller, M. (2007, January 10–14). Neural reinforcement learning controllers for a real robot application. Proceedings of the 2007 IEEE International Conference on Robotics and Automation, Roma, Italy.10.1109/ROBOT.2007.363631 ↗
13. Reinforcement learning in robotics: Applications and real-world challenges10.3390/robotics2030122 ↗
14. Kober, J., and Peters, J.R. (2009). Policy search for motor primitives in robotics. Advances in Neural Information Processing Systems, Curran Associates.10.1109/ROBOT.2009.5152577 ↗
15. Learning fast quadruped robot gaits with the RL power spline parameterization
16. Ijspeert, A.J., Nakanishi, J., and Schaal, S. (2003). Learning attractor landscapes for learning motor primitives. Advances in Neural Information Processing Systems, Curran Associates.
17. Reinforcement learning of walking behavior for a four-legged robot
18. Direct-Vision-Based Reinforcement Learning Using a Layered Neural Network10.9746/sicetr1965.37.168 ↗
19. Goto, Y., and Shibata, K. (2018, January 13–16). Emergence of higher exploration in reinforcement learning using a chaotic neural network. Proceedings of the International Conference on Neural Information Processing, Siem Reap, Cambodia.
20. Dutta, A., Dasgupta, P., and Nelson, C. (2017, January 24–28). Adaptive locomotion learning in modular self-reconfigurable robots: A game theoretic approach. Proceedings of the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, BC, Canada.10.1109/IROS.2017.8206200 ↗
21. Lample, G., and Chaplot, D.S. (2017, January 4–9). Playing FPS Games with Deep Reinforcement Learning. Proceedings of the Conference on Artificial Intelligence AAAI, San Francisco, CA, USA.10.1609/aaai.v31i1.10827 ↗
22. Deep reinforcement learning framework for autonomous driving10.2352/ISSN.2470-1173.2017.19.AVM-023 ↗
23. Ran, L., Zhang, Y., Zhang, Q., and Yang, T. (2017). Convolutional neural network-based robot navigation using uncalibrated spherical images. Sensors, 17.10.3390/s17061341 ↗
24. Generation Method of Mixed Emotional Behavior by Self-Organizing Maps in Interactive Emotion Communication
25. Face Generation Using Emotional Regions for Sensibility Robot10.1527/tjsai.21.55 ↗
26. A Model for Generating Facial Expressions Using Virtual Emotion Based on Simple Recurrent Network10.20965/jaciii.2010.p0453 ↗
27. Emotional Motion Generation Using Emotion Representation Rules Modeled for Human Affection