Multitask Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies

We introduce a new RL problem where the agent is required to execute a given subtask graph which describes a set of subtasks and their dependency. Unlike existing approaches that explicitly describe what the agent should do, our problem only describes properties of subtasks and relationships among them, which requires the agent to perform a complex reasoning to find the optimal subtask to execute. To solve this problem, we propose a neural subtask graph solver (NSS) which encodes the subtask graph using a recursive neural network. To overcome the difficulty of training, we propose a novel non-parametric gradient-based policy to pre-train our NSS agent and further finetune it through actor-critic method. The experimental results on two 2D visual domains show that our agent can perform a complex reasoning to find the optimal way of executing the subtask graph and generalize well to the unseen subtask graphs. In addition, we compare our agent with a Monte-Carlo tree search (MCTS) method showing that our method is much more efficient than MCTS, and the performance of NSS can be further improved by combining it with MCTS.

[1]  James A. Hendler,et al.  UMCP: A Sound and Complete Procedure for Hierarchical Task-network Planning , 1994, AIPS.

[2]  John F. Canny,et al.  A new algebraic method for robot motion planning and real geometry , 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[3]  Kutluhan Erol,et al.  Hierarchical task network planning: formalization, analysis, and implementation , 1996 .

[4]  Stuart J. Russell,et al.  Reinforcement Learning with Hierarchies of Machines , 1997, NIPS.

[5]  Andrew G. Barto,et al.  Building Portable Options: Skill Transfer in Reinforcement Learning , 2007, IJCAI.

[6]  Peter Auer,et al.  Finite-time Analysis of the Multiarmed Bandit Problem , 2002, Machine Learning.

[7]  Earl D. Sacerdoti,et al.  The Nonlinear Nature of Plans , 1975, IJCAI.

[8]  Rob Fergus,et al.  MazeBase: A Sandbox for Learning from Games , 2015, ArXiv.

[9]  Sridhar Mahadevan,et al.  Hierarchical Policy Gradient Algorithms , 2003, ICML.

[10]  B. Faverjon,et al.  A local based approach for path planning of manipulators with a high number of degrees of freedom , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.

[11]  Doina Precup,et al.  Temporal abstraction in reinforcement learning , 2000, ICML 2000.

[12]  John F. Canny,et al.  A Voronoi method for the piano-movers problem , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[13]  Thomas G. Dietterich.  Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition , 1999, J. Artif. Intell. Res..

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

[15]  Doina Precup,et al.  Learning Options in Reinforcement Learning , 2002, SARA.

[16]  Wei Xu,et al.  A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment , 2017, ArXiv.

[17]  Razvan Pascanu,et al.  Policy Distillation , 2015, ICLR.

[18]  Honglak Lee,et al.  Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning , 2017, ICML.

[19]  David Andre,et al.  State abstraction for programmable reinforcement learning agents , 2002, AAAI/IAAI.

[20]  David Andre,et al.  Programmable Reinforcement Learning Agents , 2000, NIPS.

[21]  Ruslan Salakhutdinov,et al.  Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning , 2015, ICLR.

[22]  Bruno Castro da Silva,et al.  Learning Parameterized Skills , 2012, ICML.

[23]  J. Sack,et al.  Minimum Decompositions of Polygonal Objects , 1985 .

[24]  Sergey Levine,et al.  High-Dimensional Continuous Control Using Generalized Advantage Estimation , 2015, ICLR.

[25]  Juan Fernández-Olivares,et al.  Temporal Enhancements of an HTN Planner , 2005, CAEPIA.

[26]  Hector Muñoz-Avila,et al.  SHOP: Simple Hierarchical Ordered Planner , 1999, IJCAI.

[27]  Dan Klein,et al.  Modular Multitask Reinforcement Learning with Policy Sketches , 2016, ICML.

[28]  Leonidas J. Guibas,et al.  Visibility-polygon search and euclidean shortest paths , 1985, 26th Annual Symposium on Foundations of Computer Science (sfcs 1985).

[29]  Lihong Li,et al.  Neuro-Symbolic Program Synthesis , 2016, ICLR.