Learning to Progressively Plan

09/30/2018
by   Xinyun Chen, et al.
0

For problem solving, making reactive decisions based on problem description is fast but inaccurate, while search-based planning using heuristics gives better solutions but could be exponentially slow. In this paper, we propose a new approach that improves an existing solution by iteratively picking and rewriting its local components until convergence. The rewriting policy employs a neural network trained with reinforcement learning. We evaluate our approach in two domains: job scheduling and expression simplification. Compared to common effective heuristics, baseline deep models and search algorithms, our approach efficiently gives solutions with higher quality.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/12/2019

Learning Improvement Heuristics for Solving the Travelling Salesman Problem

Recent studies in using deep learning to solve the Travelling Salesman P...
research
04/03/2020

Learning 2-opt Heuristics for the Traveling Salesman Problem via Deep Reinforcement Learning

Recent works using deep learning to solve the Traveling Salesman Problem...
research
11/20/2022

Learning to Search for Job Shop Scheduling via Deep Reinforcement Learning

Recent studies in using deep reinforcement learning (DRL) to solve Job-s...
research
01/18/2014

Counting-Based Search: Branching Heuristics for Constraint Satisfaction Problems

Designing a search heuristic for constraint programming that is reliable...
research
03/05/2021

Learning to Schedule DAG Tasks

Scheduling computational tasks represented by directed acyclic graphs (D...
research
07/13/2022

Simulation-guided Beam Search for Neural Combinatorial Optimization

Neural approaches for combinatorial optimization (CO) equip a learning m...
research
10/14/2009

A Component Based Heuristic Search Method with Evolutionary Eliminations

Nurse rostering is a complex scheduling problem that affects hospital pe...

Please sign up or login with your details

Forgot password? Click here to reset