Learning Generalized Reactive Policies using Deep Neural Networks

TL;DR

This paper introduces a deep neural network-based method to learn generalized reactive policies and heuristics for planning problems, enabling faster solutions with minimal domain knowledge.

Contribution

It presents a novel approach to learn generalized reactive policies directly from execution traces, reducing reliance on handcrafted features and domain expertise.

Findings

Efficiently solves large, challenging planning problems

Automatically learns heuristics for directed search algorithms

Requires minimal human input for training

Abstract

We present a new approach to learning for planning, where knowledge acquired while solving a given set of planning problems is used to plan faster in related, but new problem instances. We show that a deep neural network can be used to learn and represent a \emph{generalized reactive policy} (GRP) that maps a problem instance and a state to an action, and that the learned GRPs efficiently solve large classes of challenging problem instances. In contrast to prior efforts in this direction, our approach significantly reduces the dependence of learning on handcrafted domain knowledge or feature selection. Instead, the GRP is trained from scratch using a set of successful execution traces. We show that our approach can also be used to automatically learn a heuristic function that can be used in directed search algorithms. We evaluate our approach using an extensive suite of experiments on two challenging planning problem domains and show that our approach facilitates learning complex decision making policies and powerful heuristic functions with minimal human input. Videos of our results are available at goo.gl/Hpy4e3.