A Hybrid Transfer Algorithm for Reinforcement Learning Based on Spectral Method

For scaling up state space transfer underlying the proto-value function framework, only some basis functions corresponding to smaller eigenvalues are transferred effectively, which will result in wrong approximation of value function in the target task. In order to solve the problem, according to the fact that Laplacian eigenmap can preserve the local topology structure of state space, an improved hierarchical decomposition algorithm based on the spectral graph theory is proposed and a hybrid transfer method integrating basis function transfer with subtask optimal polices transfer is designed. At first, the basis functions of the source task are constructed using spectral method. The basis functions of target task are produced through linearly interpolating basis functions of the source task. Secondly, the produced second basis function of the target task (approximating Fiedler eigenvector) is used to decompose the target task. Then the optimal polices of subtasks are obtained using the improved hierarchical decomposition algorithm. At last, the obtained basis functions and optimal subtask polices are transferred to the target task. The proposed hybrid transfer method can directly get optimal policies of some states, reduce the number of iterations and the minimum number of basis functions needed to approximate the value function. The method is suitable for scaling up state space transfer task with hierarchical control structure. Simulation results of grid world have verified the validity of the proposed hybrid transfer method.

[1]  Chen Xing-guo,et al.  Transfer of Reinforcement Learning:The State of the Art , 2008 .

[2]  Peter Stone,et al.  Transfer Learning for Reinforcement Learning Domains: A Survey , 2009, J. Mach. Learn. Res..

[3]  Doina Precup,et al.  Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning , 1999, Artif. Intell..

[4]  Sridhar Mahadevan,et al.  Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes , 2007, J. Mach. Learn. Res..

[5]  Wang Xuesong,et al.  Q-learning System Based on Cooperative Least Squares Support Vector Machine , 2009 .

[6]  Chen Shi,et al.  Research on Reinforcement Learning Technology: A Review , 2004 .

[7]  Von-Wun Soo,et al.  AUTOMATIC COMPLEXITY REDUCTION IN REINFORCEMENT LEARNING , 2010, Comput. Intell..

[8]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[9]  Michail G. Lagoudakis,et al.  Least-Squares Policy Iteration , 2003, J. Mach. Learn. Res..

[10]  S. Mahadevan,et al.  Proto-transfer Learning in Markov Decision Processes Using Spectral Methods , 2006 .

[11]  Alicia P. Wolfe,et al.  Identifying useful subgoals in reinforcement learning by local graph partitioning , 2005, ICML.

[12]  J. Yi,et al.  An OVerview on the Adaptive Dynamic Programming Based Urban City Traffic Signal Optimal Control: An OVerview on the Adaptive Dynamic Programming Based Urban City Traffic Signal Optimal Control , 2009 .

[13]  Sridhar Mahadevan,et al.  Recent Advances in Hierarchical Reinforcement Learning , 2003, Discret. Event Dyn. Syst..

[14]  Luo Siwei and Zhao Lianwei.  Manifold Learning Algorithms Based on Spectral Graph Theory , 2006 .

[15]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[16]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  Xin Xu,et al.  Kernel-Based Least Squares Policy Iteration for Reinforcement Learning , 2007, IEEE Transactions on Neural Networks.