Inter-module credit assignment in modular reinforcement learning

Neural Networks

Volumn 16, Issue 7, 2003, Pages 985-994

  Samejima, Kazuyuki ^a,b   Doya, Kenji ^a,b   Kawato, Mitsuo ^a  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

^b JAPAN SCIENCE AND TECHNOLOGY AGENCY   (Japan)

Author keywords

Hierarchical modular architecture; Inter module credit assignment; Modular reward; MOSAIC non linear control task; Reinforcement learning

Indexed keywords

COMPUTER SIMULATION; LEARNING SYSTEMS; LINEAR CONTROL SYSTEMS; OPTIMIZATION;

REINFORCEMENT LEARNING (RL);

NEURAL NETWORKS;

ARTICLE; INDEPENDENCE; LEARNING; MATHEMATICAL COMPUTING; PRIORITY JOURNAL; REINFORCEMENT; REWARD; SIMULATION;

EID: 0742324926     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(02)00235-6     Document Type: Article

References (12)

1. Dayan P., Hinton G. Advances in neural information processing systems. Advances in neural information processing systems. vol. 5:1993;MIT press, Cambridge, MA. pp. 271-278.
2. Doya K. Reinforcement learning in continuous time and space. Neural Computation. 12:2000;219-245.
3. Doya K., Samejima K., Katagiri K., Kawato M. Multiple model-based reinforcement learning. Neural Computation. 14:2002;1347-1369.
4. Jacobs R.A., Jordan M.I., Nowlan S.J., Hinton G.E. Adaptive mixtures of local experts. Neural Computation. 3:1991;79-87.
5. Morimoto J., Doya K. Reinforcement learning of dynamic motor sequence: learning to stand up. Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. 3:1998;1721-1726.
6. Parr R., Russell S. Advances in Neural Information Processing Systems. Advances in Neural Information Processing Systems. vol. 10:1997;MIT Press, Cambridge. pp. 1043-1049.
7. Sutton R.S. Plannning by incremental dynamic programing. Birnbaum L.A., Sutton R.S., Collins G.C. Proceedings of the Eighteenth International Workshop on Machine Learning. 1991;353-357 Morgan Kaufmann, San Mateo, CA.
8. Singh S. Transfer of learning by composing solutions of elemental sequential tasks. Machine Learning. 8:1992;323-339.
9. Sutton R., Precup D., Singh S. Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence. 112:1999;181-211.
10. Sutton R.S., Barto A.G. Reinforcement learning. 1998;MIT Press, Cambridge, MA.
11. Wiering M., Schmidhuber J. HQ-learning. Adaptive Behavior. 6:(2):1997.
12. Wolpert D.M., Kawato M. Multiple paired forward and inverse models for motor control. Neural Networks. 11:1998;1317-1329.