Скачать или смотреть Rewards or Punishments: A Human-centered approach to Reinforcement Learning

Presented by Women Who Code: CONNECT Forward Virtual Conference 2020
Speaker: Favour Nerrise

Reinforcement Learning (RL) inherently models human interactions and feedback, using a model of agent actions used to maximize rewards and minimize punishments. How can RL be used to model human decision-making and processes? Do variability in ethics and other factors play a role in interpreting rewards and punishments in a human RL model?

___
Learn more about Women Who Code:
💻 WWCode Digital Events: https://www.womenwhocode.com/digital
📫 Weekly Newsletter: https://bit.ly/2LxTMps
💼 Job-Only Newsletter: https://bit.ly/3cvz70W
🙋🏾‍♀️ Events-Only Newsletter: https://bit.ly/2LBvlHn
🖥 Coding Resources: https://www.womenwhocode.com/resources
🔎 Job Board: https://www.womenwhocode.com/jobs
💌 Make a Donation: https://www.womenwhocode.com/donate