# GroomRL: jet grooming through reinforcement learning

- Institution: CERN
- Department: LPCC Workshops
- Speaker: Frederic Alexandre Dreyer
- Year: 2019
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3009314)
- Licence: [CERN](http://copyright.web.cern.ch)
- Who can watch: Tweens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

We introduce a novel implementation of a reinforcement learning algorithm which is adapted to the problem of jet grooming, a crucial component of jet physics at hadron colliders. We show that the grooming policies trained using a Deep Q-Network model outperform state-of-the-art tools used at the LHC such as Recursive Soft Drop, allowing for improved resolution of the mass of boosted objects. The algorithm learns how to optimally remove soft wide-angle radiation, allowing for a modular jet grooming tool that can be applied in a wide range of contexts..

0:00:00 Slide 1

0:00:49 Slide 2

0:01:15 Slide 3

0:01:28 Slide 4

0:01:47 Slide 5

0:02:15 Slide 6

0:03:36 Slide 7

0:04:04 Slide 8

0:05:34 Slide 9

0:05:38 Slide 10

0:06:00 Slide 11

0:07:43 Slide 12

0:08:57 Slide 13

0:09:50 Slide 14

0:10:52 Slide 15

0:12:22 Slide 16

0:13:20 Slide 17

0:14:15 Slide 18

0:15:42 Slide 19

0:17:55 Slide 20

0:18:24 Slide 21

## Lectures

1. [GroomRL: jet grooming through reinforcement learning](https://invisiblenetwork.ai/learn/cern/3009314/a9d39138f051), 21 min (CERN's player)