# Deep Reinforcement Learning and the Type IIA Landscape

- Institution: CERN
- Department: Conferences & Workshops
- Speaker: Brent Nelson
- Year: 2019
- Language: English
- Source: [CERN](https://videos.cern.ch/record/3017134)
- Licence: [CERN](http://copyright.web.cern.ch)
- Who can watch: Teens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

An artificial intelligence agent known as an asynchronous advantage actor-critic is utilized to explore type IIA compactifications with intersecting D6-branes. By reinforcement learning, the agent's performance in satisfying string consistency conditions, and finding Standard Model like configurations, is significantly improved. In one case, we demonstrate that the agent learns a human-derived strategy for finding consistent string models. In another case, where no human-derived strategy exists, the agent learns a genuinely new strategy that achieves the same goal twice as efficiently per unit time..

0:00:00 Slide 1

0:00:14 Slide 2

0:00:40 Slide 3

0:01:27 Slide 4

0:01:47 Slide 5

0:01:57 Slide 6

0:02:19 Slide 7

0:02:33 Slide 8

0:03:22 Slide 9

0:03:32 Slide 10

0:03:59 Slide 11

0:04:19 Slide 12

0:04:45 Slide 13

0:05:01 Slide 14

0:05:21 Slide 15

0:05:49 Slide 16

0:06:32 Slide 17

0:07:23 Slide 18

0:08:26 Slide 19

0:09:29 Slide 20

0:11:22 Slide 21

0:12:07 Slide 22

0:13:24 Slide 23

0:14:03 Slide 24

0:15:06 Slide 25

0:16:31 Slide 26

0:17:52 Slide 27

0:18:51 Slide 28

0:20:21 Slide 29

0:21:02 Slide 30

0:22:35 Slide 31

0:23:36 Slide 32

0:24:42 Slide 33

0:24:47 Slide 34

0:25:23 Slide 35

0:26:29 Slide 36

0:27:03 Slide 37

## Lectures

1. [Deep Reinforcement Learning and the Type IIA Landscape](https://invisiblenetwork.ai/learn/cern/3017134/acafbc5be0cb), 32 min (CERN's player)