Stochastic policy gradient reinforcement learning on a simple 3D biped

2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Volumn 3, Issue , 2004, Pages 2849-2854

  Tedrake, Russ ^a   Zhang, Teresa Weirui ^b   Seung, H Sebastian ^c  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

^b Massachusetts Institute of Technology Cambridge   (United States)

^c HOWARD HUGHES MEDICAL INSTITUTE   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BIPEDAL WALKING TECHNOLOGY; DYNAMIC WALKING; GRADIENT ALGORITHMS; ROBOT DYNAMICS;

ALGORITHMS; CONTROL EQUIPMENT; FEEDBACK CONTROL; ONLINE SYSTEMS; PRODUCT DESIGN; ROBOT LEARNING;

BIPED LOCOMOTION;

EID: 14044262287     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. J. Morimoto and C. Atkeson, "Minimax differential dynamic programming: An application to robust biped walking." Neural Information Processing Systems, 2002.
2. W. T. Miller, III, "Real-time neural network control of a biped walking robot," IEEE Control Systems Magazine, vol. 14, no. 1, pp. 41-48, Feb 1994.
3. H. Benbrahim and J. A. Franklin, "Biped dynamic walking using reinforcement learning," Robotics and Autonomous Systems, vol. 22, pp. 283-302, 1997.
4. N. Kohl and P. Stone, "Policy gradient reinforcement learning for fast quadrupedal locomotion." IEEE International Conference on Robotics and Automation, 2004.
5. T. McGeer, "Passive dynamic walking," International Journal of Robotics Research, vol. 9, no. 2, pp. 62-82, April 1990.
6. M. J. Coleman and A. Ruina, "An uncontrolled toy that can walk but cannot stand still," Physical Review Letters, vol. 80, no. 16, pp. 3658 - 3661, April 1998.
7. H. Kimura and S. Kobayashi, "An analysis of actor/critic algorithms using eligibility traces: Reinforcement learning with imperfect value functions." International Conference on Machine Learning (ICML '98), 1998, pp. 278-286.
8. J. Baxter and P. Bartlett, "Infinite-horizon policy-gradient estimation," Journal of Artificial Intelligence Research, vol. 15, pp. 319-350, 11 2001.
9. R. S. Sutton, D. McAllester, S. Singh, and Y. Mansour, "Policy gradient methods for reinforcement learning with function approximation." Advances in Neural Information Processing Systems, 1999.
10. J. E. Wilson, "Walking toy," United States Patent Office, Tech. Rep., October 15 1936.
11. R. Tedrake, T. W. Zhang, M. Fong, and H. S. Seung, "Actuating a simple 3d passive dynamic walker." IEEE International Conference on Robotics and Automation, 2004.
12. R. Williams, "Simple statistical gradient-following algorithms for connectionist reinforcement learning," Machine Learning, vol. 8, pp. 229-256, 1992.
13. S. H. Collins, M. Wisse, and A. Ruina, "A three-dimensional passive-dynamic walking robot with two legs and knees," International Journal of Robotics Research, vol. 20, no. 7, pp. 607-615, July 2001.