Reinforcement learning for a CPG-driven biped robot

Proceedings of the National Conference on Artificial Intelligence

Volumn , Issue , 2004, Pages 623-630

  Mori, Takeshi ^a   Nakamura, Yutaka ^a,c   Sato, Masa Aki ^b,c   Ishii, Shin ^a,c  

^a NARA INSTITUTE OF SCIENCE AND TECHNOLOGY   (Japan)

^b ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

^c JAPAN SCIENCE AND TECHNOLOGY AGENCY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

BIPED ROBOTS; CONTROL MECHANISM; POLICY GRADIENT METHODS; REINFORCEMENT LEARNING;

APPROXIMATION THEORY; CONTROL EQUIPMENT; ERRORS; GENETIC ALGORITHMS; NEURAL NETWORKS; PROBLEM SOLVING; ROBOT APPLICATIONS; ROBUSTNESS (CONTROL SYSTEMS);

MOBILE ROBOTS;

EID: 9444286978     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (20)

1. Barnes, D. P. 1998. Hexapodal robot locomotion over uneven terrain. In Proceedings of IEEE Conference on Control Applications, 441-445.
2. Bertsekas, D. P., and Tsitsiklis, J. N. 1996. Neuro-Dynamic Programming. Athena Scientific.
3. Bradtke, S., and Barto, A. 1996. Linear least-squares algorithms for temporal difference learning. Machine Learning 22.
4. Buehler, M.; Battaglia, R.; Cocosco, A.; Hawker, G.; Sarkis, J.; and Yamazaki, K. 1998. Scout: A simple quadruped that walks, climbs and runs. In Proceedings of the 1998 IEEE International Conference on Robotics & Automation.
5. Ekeberg, Ö. 1993. A combined neuronal and mechanical model of fish swimming. Biological Cybernetics 69:363-374.
6. Fiorillo, C. D.; Tobler, P. N.; and Schultz, W. 2003. Discrete coding of reward probability and uncertainty by dopamine neurons. SCIENCE 299:1898-1902.
7. Fukuoka, Y.; Kimura, H.; and Cohen, A. H. 2003. Adaptive dynamic walking of a quadruped robot on irregular terrain based on biological concepts. the International Journal of Robotics Research 22:187-202.
8. Grillner, S.; Wallen, P.; Brodin, L.; and Lansner, A. 1991. Neuronal network generating locomotor behavior in lamprey: circuitry, transmitters, membrane properties and simulations. Annual Review of Neuroscience 14:169-199.
9. Hirai, K.; Hirose, M.; Haikawa, Y.; and Takenaka, T. 1998. The development of honda humanoid robot. In Proceedings of the 1998 IEEE International Conference on Robotics & Automation.
10. Ijspeert, A. J. 2001. A connectionist central pattern generator for the aquatic and terrestrial gaits of a simulated salamander. Biological Cybernetics 84:331-348.
11. Konda, V. R. 2002. Actor-critic algorithms, phd thesis. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology.
12. Marbach, P., and Tsitsiklis, J. N. 2001. Simulation-based optimization of markov reward processes. IEEE Transactions on Automatic Control 46:191-209.
13. Morimoto, J., and Doya, K. 2001. Acquisition of stand-up behavior by a real robot using hierarchical reinforcement learning. Robotics and Autonomous Systems 36:37-51.
14. Ogihara, N., and Yamazaki, N. 2001. Generation of human bipedal locomotion by a bio-mimetic neuro-musculo-skeletal model. Biological Cybernetics 84:1-11.
15. Sato, M., and Ishii, S. 1999. Reinforcement learning based on on-line em algorithm. In Advances in Neural Information Processing Systems, volume 11, 1052-1058.
16. Sato, M. 1990. A real time learning algorithm for recurrent analog neural networks. Biological Cybernetics 62:237-241.
17. Sutton, R., and Barto, A. 1998. Reinforcement Learning: An Introduction. MIT Press.
18. Sutton, R. S.; McAllester, D.; Singh, S.; and Mansour, Y. 2000. Policy gradient methods for reinforcement learning with function approximation. In Advances in Neural Information Processing Systems, volume 12, 1057-1063.
19. Taga, G.; Yamaguchi, Y.; and Shimizu, H. 1991. Self-organized control of bipedal locomotion by neural oscillators in unpredictable environment. Biological Cybernetics 65:147-159.
20. Williams, R. 1992. Simple statistical gradient following algorithms for connectionist reinforcement learning. Machine Learning 8:279-292.