论文信息 - Transfer of Learning Across Compositions of Sequentail Tasks - 字舞流文

Transfer of Learning Across Compositions of Sequentail Tasks

Satinder P. Singh | Satinder Singh

[1] Michael I. Jordan,et al. Task Decomposition Through Competition in a Modular Connectionist Architecture: The What and Where Vision Tasks , 1990, Cogn. Sci..

[2] Andrew G. Barto,et al. On the Computational Economics of Reinforcement Learning , 1991 .

[3] Dana H. Ballard,et al. Active Perception and Reinforcement Learning , 1990, Neural Computation.

[4] Richard S. Sutton,et al. Integrated Architectures for Learning, Planning, and Reacting Based on Approximating Dynamic Programming , 1990, ML.

[5] C. Watkins. Learning from delayed rewards , 1989 .

[6] Richard S. Sutton,et al. Sequential Decision Problems and Neural Networks , 1989, NIPS 1989.

[7] Richard S. Sutton,et al. Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.