reinforcement learning for railway scheduling · reinforcement learning for railway scheduling...

14
Reinforcement Learning for Railway Scheduling Overcoming Data Sparseness through Simulations Dr. Erik Nygren Research and Innovation Lab Swiss Federal Railway

Upload: others

Post on 31-Jul-2020

2 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Reinforcement Learning for Railway Scheduling · Reinforcement Learning for Railway Scheduling Overcoming Data Sparseness through Simulations Dr. Erik Nygren Research and Innovation

Reinforcement Learning

for Railway Scheduling

Overcoming Data Sparseness through Simulations

Dr. Erik Nygren Research and Innovation Lab Swiss Federal Railway

Page 2: Reinforcement Learning for Railway Scheduling · Reinforcement Learning for Railway Scheduling Overcoming Data Sparseness through Simulations Dr. Erik Nygren Research and Innovation

© SBB • Solution Center Infrastructure • Research & Innovation • October 2017 2

Swiss Railway Network. A Complex Dynamical System.

Influencing Factors Facts

1

10,000

1,210,000

Weather People

Infrastructure Events

12,997

Most dense network 33,000

210,000 t

1t

31,266

3,230 km

KM

Energy

Page 3: Reinforcement Learning for Railway Scheduling · Reinforcement Learning for Railway Scheduling Overcoming Data Sparseness through Simulations Dr. Erik Nygren Research and Innovation

© SBB • Solution Center Infrastructure • Research & Innovation • October 2017 3

Train Dispatching and Scheduling. Challenges in the Worlds Densest Train Network.

RCS

Train runs

Production

Timetable

Page 4: Reinforcement Learning for Railway Scheduling · Reinforcement Learning for Railway Scheduling Overcoming Data Sparseness through Simulations Dr. Erik Nygren Research and Innovation

Evolution of Dispatching. Towards Full Automation.

Today

Future

Past

© SBB • Solution Center Infrastructure • Research & Innovation • October 2017 4

Page 5: Reinforcement Learning for Railway Scheduling · Reinforcement Learning for Railway Scheduling Overcoming Data Sparseness through Simulations Dr. Erik Nygren Research and Innovation

© SBB • Solution Center Infrastructure • Research & Innovation • October 2017 5

Automated Train Dispatching. Current Challenges.

Big Data

Big Data: Not enough relevant information

Automated

Dispatching

Learning

Measure-

ments Action

Page 6: Reinforcement Learning for Railway Scheduling · Reinforcement Learning for Railway Scheduling Overcoming Data Sparseness through Simulations Dr. Erik Nygren Research and Innovation

© SBB • Solution Center Infrastructure • Research & Innovation • October 2017 6

Reinforcement Learning for Railway Dispatching. Overcoming Data Sparseness through Simulations.

WIP

Measure- ments Action

Validation

Data generation

Learning

Learning

Action

Artificial Data

Big Data

High Performance Simulation

Page 7: Reinforcement Learning for Railway Scheduling · Reinforcement Learning for Railway Scheduling Overcoming Data Sparseness through Simulations Dr. Erik Nygren Research and Innovation

© SBB • Solution Center Infrastructure • Research & Innovation • October 2017 7

High Performance Simulations. Unleashing the Power of Parallel Computing.

DGX-1 High Performance Simulations

Time speedup Scenario variations Influencing factor analysis

Page 8: Reinforcement Learning for Railway Scheduling · Reinforcement Learning for Railway Scheduling Overcoming Data Sparseness through Simulations Dr. Erik Nygren Research and Innovation

© SBB • Solution Center Infrastructure • Research & Innovation • October 2017 8

Preliminary Results. Visualization of Simulation Results.

2h realtime

500x

5000x Simulation speed

Visualization speed

Page 9: Reinforcement Learning for Railway Scheduling · Reinforcement Learning for Railway Scheduling Overcoming Data Sparseness through Simulations Dr. Erik Nygren Research and Innovation

© SBB • Solution Center Infrastructure • Research & Innovation • October 2017 9

Reinforcement Learning. Playing the Dispatcher Game.

Action

Reward

DGX-1 High Performance Simulations

Artificial Data

DGX-1 Automated Dispatcher

Page 10: Reinforcement Learning for Railway Scheduling · Reinforcement Learning for Railway Scheduling Overcoming Data Sparseness through Simulations Dr. Erik Nygren Research and Innovation

© SBB • Solution Center Infrastructure • Research & Innovation • October 2017 10

Machine Learning on Artificial Data. Generating, Evaluating and Optimizing Train Dispatching.

Automated Dispatcher

Reinforcement Learning

Tree Search

Evolutionary Strategies

Building Blocks Variable Topologies

1

2

3

Mixed Integer Linear Programming

Genetic Algorithm

Page 11: Reinforcement Learning for Railway Scheduling · Reinforcement Learning for Railway Scheduling Overcoming Data Sparseness through Simulations Dr. Erik Nygren Research and Innovation

© SBB • Solution Center Infrastructure • Research & Innovation • October 2017 11

Current State... And Future Expected Reward.

DGX-1 High Performance Simulations

DGX-1 Automated Dispatcher

Fully Automated Process

Train runs

Production

Timetable

Page 12: Reinforcement Learning for Railway Scheduling · Reinforcement Learning for Railway Scheduling Overcoming Data Sparseness through Simulations Dr. Erik Nygren Research and Innovation

Take Home.

Big Data Big Information

Page 13: Reinforcement Learning for Railway Scheduling · Reinforcement Learning for Railway Scheduling Overcoming Data Sparseness through Simulations Dr. Erik Nygren Research and Innovation

© SBB • Solution Center Infrastructure • Research & Innovation • October 2017 13

Take Home.

AI

Model

Big Data Big Information

Dr. Erik Nygren

[email protected]

AI Researcher

Research Team

Page 14: Reinforcement Learning for Railway Scheduling · Reinforcement Learning for Railway Scheduling Overcoming Data Sparseness through Simulations Dr. Erik Nygren Research and Innovation

© SBB • Solution Center Infrastructure • Research & Innovation • October 2017 14

Reward Function. How to Reward an Artificial Dispatcher.

Reward