SBB Improves Train Management with NVIDIA DGX-1
January 23, 2019
5,063
164
145
6.10%
Search the Record
IndexedEvery word spoken in this episode is indexed. Type any phrase to jump straight to the moment it was said.
Type any word or phrase that may have been spoken. Click a result to seek the player to that exact moment.
Try a name, a topic, or a quoted line
Nvidia Episodes Around January 23, 2019
See what was published immediately before and after this episode.
0:55Now PlayingSBB Improves Train Management with NVIDIA DGX-1
YouTube Description
as posted by the channelThe Swiss Federal Railway (SBB) dispatches 10,671 trains every day, serving 1.26 million riders across 3,232 km of track. This task is getting increasingly complex as due to more trains, more passengers and more routes.
Adrian Egli from SBB discusses why they chose to run multi-agent reinforcement learning on NVIDIA’s DGX-1 to solve this challenge, whilst ensuring passenger safety and the timely arrivals and departures of trains. Thanks to the power of NVIDIA’s DGX-1, simulating the whole Swiss railway network now takes under 3 seconds.
Links & Promotions
Guests & Subjects Covered
Sentinel Indexing in Progress
Metadata and chapters are available. Claim extraction for this episode is pending.
All video content is delivered via YouTube embedded players in accordance with the YouTube Terms of Service. Sentinel provides research tools that promote discovery and accountability across political media.