Video Demo: Deep Reinforcement Learning for Coordination in Traffic Light Control
| Authors | |
|---|---|
| Publication date | 2016 |
| Host editors |
|
| Book title | BNAIC 2016 : Benelux Conference on Artificial Intelligence |
| Book subtitle | proceedings of the Twenty-Eight Benelux Conference on Artificial Intelligence : Amsterdam, November 10-11, 2016 |
| Series | BNAIC |
| Event | Annual Benelux Conference on Artificial Intelligence |
| Pages (from-to) | 239-240 |
| Publisher | Amsterdam: Vrije Universiteit, Department of Computer Sciences |
| Organisations |
|
| Abstract | This video demonstration contrasts two approaches to coordination in traffic light control using reinforcement learning: earlier work, based on a deconstruction of the state space into a linear combination of vehicle states, and our own approach based on the Deep Q-learning algorithm. |
| Document type | Conference contribution |
| Language | English |
| Published at | http://bnaic2016.cs.vu.nl/index.php/proceedings |
| Other links | https://www.youtube.com/watch?v=apmxBzHiXHY |
| Downloads |
Video Demo
(Final published version)
|
| Permalink to this page | |