Many complex real-world tasks are composed of several levels of sub-tasks. Humans leverage these hierarchical structures to accelerate the learning process and achieve better generalization. In this work, we study the inductive bias and propose Ordered Memory Policy Network (OMPN) to discover subtask hierarchy by learning from demonstration. The discovered subtask hierarchy could be used to perform task decomposition, recovering the subtask boundaries in an unstruc-tured demonstration. Experiments on Craft and Dial demonstrate that our modelcan achieve higher task decomposition performance under both unsupervised and weakly supervised settings, comparing with strong baselines. OMPN can also bedirectly applied to partially observable environments and still achieve higher task decomposition performance. Our visualization further confirms that the subtask hierarchy can emerge in our model.
Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks and Autoregressive Policy Decomposition
Czech Technical University in Prague（布拉格捷克技术大学）；Artificial Intelligence Center, Department of Computer Science, Faculty of Electrical Engineering（电气工程学院计算机科学系人工智能中心）
POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition
Cornell University（康奈尔大学）；University of Washington（华盛顿大学）；Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）
Efficient Offline Learning of Ranking Policies via Top-$k$ Policy Decomposition
Institute of Science Tokyo（东京科学大学）；Keio University（庆应义塾大学）；Cornell University（康奈尔大学）；Yale University（耶鲁大学）；LY Corporation；Hanjuku-kaso, Co., Ltd.（Hanjuku-kaso株式会社）
Dealing with Non-Stationarity in MARL via Trust-Region Decomposition
East China Normal University（华东师范大学）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人研究院）
Ordered Preference Elicitation Strategies for Supporting Multi-Objective Decision Making
Vrije Universiteit Brussel（布鲁塞尔自由大学）；University of Oxford（牛津大学）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；City of Amsterdam, Signal Control Design and Analysis（阿姆斯特丹市信号控制设计与分析部门）；Delft University of Technology（代尔夫特理工大学）
A Policy Decomposition Framework for Dynamic Order Fulfillment Operations
Massachusetts Institute of Technology（麻省理工学院）；School of Industrial and Intelligent Systems Engineering, Tel Aviv University（特拉维夫大学工业与智能系统工程学院）；Otto-von-Guericke Universitat Magdeburg（马格德堡奥托·冯·格里克大学）
Offline Multi-agent Reinforcement Learning via Sequential Score Decomposition
School of Data Science, The Chinese University of Hong Kong, Shenzhen, China（香港中文大学（深圳）数据科学学院）；School of Computer Science, Tongji University, Shanghai, China（同济大学计算机科学学院）；Vector Institute（向量研究所）
