Time-based Dynamic Controllability of Disjunctive Temporal Networks with Uncertainty: A Tree Search Approach with Graph Neural Network Guidance

Scheduling in the presence of uncertainty is an area of interest in artificial intelligence due to the large number of applications. We study the problem of dynamic controllability (DC) of disjunctive temporal networks with uncertainty (DTNU), which seeks a strategy to satisfy all constraints in response to uncontrollable action durations. We introduce a more restricted, stronger form of controllability than DC for DTNUs, time-based dynamic controllability (TDC), and present a tree search approach to determine whether or not a DTNU is TDC. Moreover, we leverage the learning capability of a message passing neural network (MPNN) as a heuristic for tree search guidance. Finally, we conduct experiments for which the tree search shows superior results to state-of-the-art timed-game automata (TGA) based approaches, effectively solving fifty percent more DTNU problems on a known benchmark. We also observe that MPNN tree search guidance leads to substantial performance gains on benchmarks of more complex DTNUs, with up to eleven times more problems solved than the baseline with the same time budget.

[1]  Brian C. Williams,et al.  Complexity Bounds for the Controllability of Temporal Networks with Conditions, Disjunctions, and Uncertainty , 2019, Artif. Intell..

[2]  Jie Chen,et al.  Adaptive Planner Scheduling with Graph Neural Networks , 2018, ArXiv.

[3]  Andrea Lodi,et al.  Exact Combinatorial Optimization with Graph Convolutional Neural Networks , 2019, NeurIPS.

[4]  Marco Roveri,et al.  Dynamic Controllability of Disjunctive Temporal Networks: Validation and Synthesis of Executable Strategies , 2016, AAAI.

[5]  Roberto Proietti,et al.  Deep-RMSA: A Deep-Reinforcement-Learning Routing, Modulation and Spectrum Assignment Agent for Elastic Optical Networks , 2018, 2018 Optical Fiber Communications Conference and Exposition (OFC).

[6]  Ioannis Tsamardinos,et al.  A Probabilistic Approach to Robust Execution of Temporal Plans with Uncertainty , 2002, SETN.

[7]  Thierry Vidal,et al.  Handling contingency in temporal constraint networks: from consistency to controllabilities , 1999, J. Exp. Theor. Artif. Intell..

[8]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[9]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[10]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[11]  Max Welling,et al.  Attention Solves Your TSP , 2018, ArXiv.

[12]  Richard S. Zemel,et al.  Gated Graph Sequence Neural Networks , 2015, ICLR.

[13]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[14]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[15]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[16]  Razvan Pascanu,et al.  Interaction Networks for Learning about Objects, Relations and Physics , 2016, NIPS.

[17]  Chi Harold Liu,et al.  Experience-driven Networking: A Deep Reinforcement Learning based Approach , 2018, IEEE INFOCOM 2018 - IEEE Conference on Computer Communications.

[18]  Nicola Muscettola,et al.  Temporal Dynamic Controllability Revisited , 2005, AAAI.

[19]  Paul Morris,et al.  Dynamic Controllability and Dispatchability Relationships , 2014, CPAIOR.

[20]  Zhuwen Li,et al.  Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search , 2018, NeurIPS.

[21]  Tristan Cazenave,et al.  Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[22]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Shirin Sohrabi,et al.  Deep Learning for Cost-Optimal Planning: Task-Dependent Planner Selection , 2019, AAAI.

[24]  Albert Cabellos-Aparicio,et al.  Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN , 2019, SOSR.

[25]  Philip S. Yu,et al.  A Comprehensive Survey on Graph Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[26]  R. Zemel,et al.  Neural Relational Inference for Interacting Systems , 2018, ICML.