# A Crash Course on Reinforcement Learning

- Institution: CERN
- Department: Inverted CSC
- Speaker: Felix Wagner
- Year: 2023
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3000256)
- 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)

Supervised and unsupervised machine learning has shown great performance in finding mappings between probability distributions, as e.g. in classification problems or for artificial data generation. A more difficult class of problems is decision-making, e.g. controlling dynamical systems or building mathematical algorithms because the framework requires additional time-ordering. Reinforcement learning (RL) was successful in solving such problems, e.g. in finding strategies for games, optimizing algorithms for high-performance computing, and controlling magnetic fields for nuclear fusion reactors and particle accelerators. In this lecture, I will provide an introduction to the framework, with pedagogical examples, mathematical details, and applications in particle physics. In detail, I will cover: 1) Markov decision processes (MDPs) as the mathematical foundation of RL; 2) Solving small MPDs with tabular methods; 3) Solving large MDPs with policy gradient methods..

0:00:00 Slide 1

0:02:40 Slide 2

0:05:08 Slide 3

0:06:17 Slide 4

0:07:46 Slide 5

0:11:33 Slide 6

0:16:44 Slide 7

0:17:57 Slide 8

0:21:09 Slide 9

0:24:09 Slide 10

0:27:01 Slide 11

0:30:54 Slide 12

0:33:59 Slide 13

0:36:01 Slide 14

0:40:29 Slide 15

0:43:05 Slide 16

0:45:23 Slide 17

0:47:25 Slide 18

0:48:32 Slide 19

0:51:11 Slide 20

0:52:25 Slide 21

0:53:48 Slide 22

## Lectures

1. [A Crash Course on Reinforcement Learning](https://invisiblenetwork.ai/learn/cern/3000256/bac63100056e), 56 min (CERN's player)