Improving state-action space exploration in reinforcement learning using geometric properties
暂无分享,去创建一个
[1] Richard S. Sutton,et al. Integrated Architectures for Learning, Planning, and Reacting Based on Approximating Dynamic Programming , 1990, ML.
[2] Brian C. Williams,et al. Qualitative Reasoning about Physical Systems: A Return to Roots , 1991, Artif. Intell..
[3] Richard S. Sutton,et al. Generalization in ReinforcementLearning : Successful Examples UsingSparse Coarse , 1996 .
[4] Symmetry of Stochastic Equations , 2004, math-ph/0401025.
[5] Peter E. Hydon,et al. Symmetry Methods for Differential Equations: A Beginner's Guide , 2000 .
[6] Shane Legg,et al. Human-level control through deep reinforcement learning , 2015, Nature.
[7] R. Kozlov. On symmetries of stochastic differential equations , 2012 .
[8] Csaba Szepesvári,et al. Algorithms for Reinforcement Learning , 2010, Synthesis Lectures on Artificial Intelligence and Machine Learning.
[9] R. Kozlov. On symmetries of the Fokker–Planck equation , 2013 .
[10] Richard S. Sutton,et al. Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.
[11] W. Marsden. I and J , 2012 .
[12] F. C. D. Vecchi,et al. Symmetries of stochastic differential equations: A geometric approach , 2015, 1512.05215.
[13] Sean P. Meyn,et al. An analysis of reinforcement learning with function approximation , 2008, ICML '08.
[14] Benjamin Kuipers,et al. Reasoning with Qualitative Models , 1993, Artif. Intell..