Exponentiated Gradient Methods for Reinforcement Learning
暂无分享,去创建一个
[1] Manfred K. Warmuth,et al. Exponentiated Gradient Versus Gradient Descent for Linear Predictors , 1997, Inf. Comput..
[2] James P. Callan,et al. Training algorithms for linear text classifiers , 1996, SIGIR '96.
[3] James P. Callan,et al. Text-Based Information Retrieval Using Exponentiated Gradient Descent , 1996, NIPS.
[4] W. T. Miller,et al. CMAC: an associative neural network alternative to backpropagation , 1990, Proc. IEEE.
[5] HadzikadicMirsad,et al. Learning to Predict , 1997 .
[6] R. Sutton,et al. Empirical Comparison of Gradient Descent and Exponentiated Gradient Descent in Supervised and Reinforcement Learning , 1996 .
[7] Richard S. Sutton,et al. Reinforcement Learning with Replacing Eligibility Traces , 2005, Machine Learning.
[8] Mahesan Niranjan,et al. On-line Q-learning using connectionist systems , 1994 .
[9] N. Littlestone. Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm , 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).
[10] Richard S. Sutton,et al. Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding , 1995, NIPS.