DeepAI AI Chat
Log In Sign Up

Learning Task Decomposition with Ordered Memory Policy Network

by   Yuchen Lu, et al.

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.


page 7

page 8

page 14

page 15

page 20


TACO: Learning Task Decomposition via Temporal Alignment for Control

Many advanced Learning from Demonstration (LfD) methods consider the dec...

Totally and Partially Ordered Hierarchical Planners in PDDL4J Library

In this paper, we outline the implementation of the TFD (Totally Ordered...

Unsupervised Hierarchical Concept Learning

Discovering concepts (or temporal abstractions) in an unsupervised manne...

Characterizing tradeoffs between teaching via language and demonstrations in multi-agent systems

Humans teach others about the world through language and demonstration. ...

Learning Representations for Control with Hierarchical Forward Models

Learning control from pixels is difficult for reinforcement learning (RL...

Unsupervised Discovery of 3D Hierarchical Structure with Generative Diffusion Features

Inspired by recent findings that generative diffusion models learn seman...

Model-agnostic Measure of Generalization Difficulty

The measure of a machine learning algorithm is the difficulty of the tas...