Parallel reinforcement learning: a framework and case study

In this paper, a new machine learning framework is developed for complex system control, called parallel reinforcement learning. To overcome data deficiency of current data-driven algorithms, a parallel system is built to improve complex learning system by self-guidance. Based on the Markov chain ( MC ) theory, we combine the transfer learning, predictive learning, deep learning and reinforcement learning to tackle the data and action processes and to express the knowledge. Parallel reinforcement learning framework is formulated and several case studies for real-world problems are finally introduced.

[1]  Dimitar Filev,et al.  Generalized Markov Models for Real-Time Modeling of Continuous Systems , 2014, IEEE Transactions on Fuzzy Systems.

[2]  Huaguang Zhang,et al.  Adaptive Dynamic Programming: An Introduction , 2009, IEEE Computational Intelligence Magazine.

[3]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[4]  Ali Farhadi,et al.  Target-driven visual navigation in indoor scenes using deep reinforcement learning , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[5]  Fei-Yue Wang,et al.  Artificial Societies for Integrated and Sustainable Development of Metropolitan Systems , 2004, IEEE Intell. Syst..

[6]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[7]  Fei-Yue Wang,et al.  Toward a Paradigm Shift in Social Computing: The ACP Approach , 2007, IEEE Intell. Syst..

[8]  Nanning Zheng,et al.  Parallel learning: a perspective and a framework , 2017, IEEE/CAA Journal of Automatica Sinica.

[9]  David Silver,et al.  Deep Reinforcement Learning from Self-Play in Imperfect-Information Games , 2016, ArXiv.

[10]  Ilya Kolmanovsky,et al.  Markov chain modeling approaches for on board applications , 2010, Proceedings of the 2010 American Control Conference.

[11]  Fei-Yue Wang,et al.  Traffic Flow Prediction With Big Data: A Deep Learning Approach , 2015, IEEE Transactions on Intelligent Transportation Systems.

[12]  Nanning Zheng,et al.  Parallel vision for perception and understanding of complex scenes: methods, framework, and perspectives , 2017, Artificial Intelligence Review.

[13]  Yuval Tassa,et al.  Data-efficient Deep Reinforcement Learning for Dexterous Manipulation , 2017, ArXiv.

[14]  Guoyuan Wu,et al.  Deep reinforcement learning-based vehicle energy efficiency autonomous learning system , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[15]  Danijar Hafner,et al.  Deep Reinforcement Learning From Raw Pixels in Doom , 2016, ArXiv.

[16]  Fei-Yue Wang,et al.  The Emergence of Intelligent Enterprises: From CPS to CPSS , 2010, IEEE Intelligent Systems.

[17]  Regina Barzilay,et al.  Language Understanding for Text-based Games using Deep Reinforcement Learning , 2015, EMNLP.

[18]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[19]  Svetlana Lazebnik,et al.  Active Object Localization with Deep Reinforcement Learning , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[20]  Alex Graves,et al.  Playing Atari with Deep Reinforcement Learning , 2013, ArXiv.

[21]  Honglak Lee,et al.  Deep Learning for Reward Design to Improve Monte Carlo Tree Search in ATARI Games , 2016, IJCAI.

[22]  Dongpu Cao,et al.  Reinforcement Learning Optimized Look-Ahead Energy Management of a Parallel Hybrid Electric Vehicle , 2017, IEEE/ASME Transactions on Mechatronics.

[23]  Fei-Yue Wang,et al.  Data-Driven Intelligent Transportation Systems: A Survey , 2011, IEEE Transactions on Intelligent Transportation Systems.

[24]  Fei-Yue Wang,et al.  Parallel Control and Management for Intelligent Transportation Systems: Concepts, Architectures, and Applications , 2010, IEEE Transactions on Intelligent Transportation Systems.

[25]  Erik Frisk,et al.  Driving Cycle Adaption and Design Based on Mean Tractive Force , 2013 .

[26]  Erik Frisk,et al.  Driving Cycle Equivalence and Transformation , 2017, IEEE Transactions on Vehicular Technology.

[27]  Dongpu Cao,et al.  Parallel driving in CPSS: a unified approach for transport automation and vehicle intelligence , 2017, IEEE/CAA Journal of Automatica Sinica.