A parameter control method in reinforcement learning to rapidly follow unexpected environmental changes.
暂无分享,去创建一个
[1] Kenji Doya,et al. Metalearning and neuromodulation , 2002, Neural Networks.
[2] Richard S. Sutton,et al. Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.
[3] James S. Albus,et al. I A New Approach to Manipulator Control: The I Cerebellar Model Articulation Controller , 1975 .
[4] Peter Dayan,et al. Technical Note: Q-Learning , 2004, Machine Learning.
[5] Richard S. Sutton,et al. Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding , 1995, NIPS.
[6] Junichiro Yoshimoto,et al. Control of exploitation-exploration meta-parameter in reinforcement learning , 2002, Neural Networks.
[7] James S. Albus,et al. New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC)1 , 1975 .
[8] Kenji Doya,et al. Meta-learning in Reinforcement Learning , 2003, Neural Networks.
[9] S. Sara,et al. Response to Novelty and its Rapid Habituation in Locus Coeruleus Neurons of the Freely Exploring Rat , 1995, The European journal of neuroscience.
[10] J. Leander,et al. Selective Serotonin Reuptake Inhibitors Decrease Impulsive Behavior as Measured by an Adjusting Delay Procedure in the Pigeon , 2002, Neuropsychopharmacology.
[11] F. Fadda,et al. Hippocampal acetylcholine release correlates with spatial learning performance in freely moving rats , 2000, Neuroreport.