A policy representation using weighted multiple normal distribution real-time reinforcement learning feasible for varying optimal actions

Transactions of the Japanese Society for Artificial Intelligence

Volumn 18, Issue 6, 2003, Pages 316-324

  Kimura, Hajime ^a   Aramaki, Takeshi ^a   Kobayashi, Shigenobu ^a  

^a TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Actor critic; Hierarchical representation; Reinforcement learning; Robotics

Indexed keywords

ACTOR-CRITICS; HIERARCHICAL POLICIES; HIERARCHICAL REPRESENTATION; REINFORCEMENT LEARNING;

ALGORITHMS; COMPUTER SIMULATION; NORMAL DISTRIBUTION; PROBLEM SOLVING; ROBOTICS; SENSORS;

ROBOT LEARNING;

EID: 18444390265     PISSN: 13460714     EISSN: 13468030     Source Type: Journal    
DOI: 10.1527/tjsai.18.316     Document Type: Article

References (17)

1. Japanese only
2. Japanese only
3. Japanese only
4. Japanese only
5. Japanese only
6. Japanese only
7. Japanese only
8. [Lin 96] C. J. Lin and C. T. Lin: Reinforcement Learning for An ART-Based Fuzzy Adaptive Learning Control Network, IEEE Transactions on Neural Networks, Vol.7, No. 3, pp.709-731 (1996).
9. [Lin 99] C. T. Lin and I. F. Chung: A Reinforcement Neuro-Fuzzy Combiner for Multiobjective Control, IEEE Transactions on Systems, Man, and Cybernetics-Part B: Cybernetcs, Vol.29, No.6, pp.726-744, 1999.
10. Japanese only
11. Japanese only
12. [Santamaria 98] J. C. Santamaria, R. S. Sutton and A. Ram: Experiments with Reinforcement Learning in Problems with Continuous State and Action Spaces, Adaptive Behavior 6 (2), pp.163-218 (1998).
13. [Sutton 98] R. S. Sutton and A. Barto: Reinforcement Learning: An Introduction, A Bradford Book, The MIT Press (1998).
14. [Sutton 00] 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 12 (NIPS 12), pp. 1057-1063 (2000).
15. [Yoshimoto 00] J. Yoshimoto, S. Ishii and M. Sato: On-line EM reinforcement learning, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN 2000), III, pp. 163-168, (2000).
16. [Watkins 92] C. J. C. H. Watkins and P. Dayan: Technical Note: Q-Learning, Machine Learning 8, pp.279-292 (1992).
17. [Williams 92] R. J. Williams: Simple Statistical Gradient Following Algorithms for Connectionist Reinforcement Learning, Machine Learning 8, pp. 229-256 (1992).