Application of actor-critic learning to adaptive state space construction

Proceedings of 2004 International Conference on Machine Learning and Cybernetics

Volumn 5, Issue , 2004, Pages 2985-2990

  Cheng, Yu Hu ^a   Yi, Jian Qiang ^a   Zhao, Dong Bin ^a  

^a INSTITUTE OF AUTOMATION   (China)

Author keywords

Actor Critic architecture; Inverted pendulum; Reinforcement learning; State space construction

Indexed keywords

ADAPTIVE CONTROL SYSTEMS; COMPUTER SIMULATION; FUNCTION EVALUATION; LEARNING ALGORITHMS; NEURAL NETWORKS; PENDULUMS; RANDOM PROCESSES; SIGNAL PROCESSING;

ACTOR CRITIC ARCHITECTURE; INVERTED PENDULUM; REINFORCEMENT LEARNING; STATE SPACE CONSTRUCTION;

LEARNING SYSTEMS;

EID: 6344223423     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. Kaebling L P et al. Reinforcement Learning: A Survey. Journal of Artificial Intelligence Research, No. 4, pp. 237-285, 1996.
2. Barto A G, Sutton R S, and Anderson C W. Neuron-like elements that can solve difficult learning control problems. IEEE Trans. System, Man, Cybernetics, No. 13, pp. 835-846, 1983.
3. Anderson C W. Learning to control an inverted pendulum using neural networks. IEEE Control System Magazine, Vol 9, No. 3, pp. 31-37, 1989.
4. Lin C T, Lee C S G. Reinforcement structure/parameter learning for neural-network-based fuzzy logic control systems. IEEE Trans on fuzzy systems, Vol 2, No. 1, pp. 41-63, 1994.
5. Samejima K, Omori T. Adaptive internal state space construction method for reinforcement learning of a real-world agent. Neural Network, Vol 12, No. 7, pp. 1143-1155, 1999.
6. Moody J, Darken C. Fast Learning in Networks of Locally-tuned Processing Units. Neural Computation, No. 1, pp. 281-294, 1989.
7. Platt J C. A resource-allocating network for function interpolation. Neural Computation, No.1 pp. 213-225, 1991.
8. Michie D, Chanbers R A. BOXES: An experiment in adaptive control. Machine Intelligence 2. Edinburgh: Oliver and Boyd, 1968.