Binary action search for learning continuous-action control policies

Proceedings of the 26th International Conference On Machine Learning, ICML 2009

Volumn , Issue , 2009, Pages 793-800

  Pazis, Jason ^a   Lagoudakis, Michail G ^a  

^a TECHNICAL UNIVERSITY OF CRETE   (Greece)

Author keywords

[No Author keywords available]

Indexed keywords

ACTION POLICIES; ACTION SPACES; AUGMENTED STATE SPACE; CONTINUOUS STATE; CONTROL POLICY; DISCRETIZATIONS; DOUBLE INTEGRATOR; INVERTED PENDULUM; LEAST SQUARE; NOVEL METHODS; POLICY ITERATION; REAL-WORLD PROBLEM; REINFORCEMENT LEARNING METHOD; STOCHASTIC PROCESS;

EDUCATION; RANDOM PROCESSES; REINFORCEMENT; REINFORCEMENT LEARNING; ROBOT LEARNING;

LEARNING ALGORITHMS;

EID: 71149094455     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. Baird, L. C., & Klopf, A. H. (1993). Reinforcement learning with high-dimensional, continuous actions (Technical Report WL-TR-93-1147). Wright Laboratory.
2. Ernst, D., Geurts, P., & Wehenkel, L. (2005). Tree-based batch mode reinforcement learning. Journal of Machine Learning Research, 6, 503-556.
3. Gaskett, C., Wettergreen, D., & Zelinsky, E. (1999). Q-learning in continuous state and action spaces. Proceedings of the 12th Australian Joint Conference on Artificial Intelligence (pp. 417-428).
4. Gross, H. M., Stephan, V., & Krabbes, M. (1998). A neural field approach to topological reinforcement learning in continuous action spaces. Proceedings of the IEEE Intl Joint Conference on Neural Networks (pp. 1992-1997).
5. Kimura, H., & Kobayashi, S. (1998). Reinforcement learning for continuous action using stochastic gradient ascent. Proceedings of the 5th Intl Conference on Intelligent Autonomous Systems (pp. 288-295).
6. Lagoudakis, M. G., & Parr, R. (2003). Least-squares policy iteration. Journal of Machine Learning Research, 4, 1107-1149.
7. Lazaric, A., Restelli, M., & Bonarini, A. (2008). Reinforcement learning in continuous action spaces through sequential monte carlo methods. In Advances in neural information processing systems 20, 833-840.
8. Millán, J. D. R., Posenato, D., & Dedieu, E. (2002). Continuous-action Q-learning. Machine Learning, 49, 247-265.
9. Pazis, J., & Lagoudakis, M. G. (2009). Learning continuous-action control policies. Proceedings of the IEEE Intl Symposium on Adaptive Dynamic Programming and Reinforcement Learning (pp. 169-176).
10. Peters, J., & Schaal, S. (2006). Policy gradient methods for robotics. Proceedings of the IEEE/RSJ Intl Conference on Intelligent Robots and Systems (pp. 2219-2225).
11. Prokhorov, D., & Wunsch, D. (1997). Adaptive critic designs. IEEE Trans. on Neural Networks, 8, 997-1007.
12. Riedmiller, M. (1997). Application of a self-learning controller with continuous control signals based on the DOE-approach. Proceedings of the European Symposium on Neural Networks (pp. 237-242).
13. Sallans, B., & Hinton, G. E. (2004). Reinforcement learning with factored states and actions. Journal of Machine Learning Research, 5, 1063-1088.
14. Santamaría, J. C., Sutton, R. S., & Ram, A. (1998). Experiments with reinforcement learning in problems with continuous state and action spaces. Adaptive Behavior, 6, 163-218.
15. Strösslin, T., & Gerstner, W. (2003). Reinforcement learning in continuous state and action space. Proceedings of the Intl Conference on Artificial Neural Networks.
16. Sutton, R., & Barto, A. (1998). Reinforcement learning: An introduction. The MIT Press.
17. Touzet, C. (1997). Neural reinforcement learning for behaviour synthesis. Robotics and Autonomous Systems, 22, 251-281.
18. Wang, H., Tanaka, K., & Griffin, M. (1996). An approach to fuzzy control of nonlinear systems: Stability and design issues. IEEE Trans. on Fuzzy Systems, 4, 14-23.