Welcome sentient being! We appreciate you reading the site, but contributions are even better. To get started, simply create an account and make your first edit today!

People for the Ethical Treatment of Reinforcement Learners

From H+Pedia
Jump to: navigation, search

People for the Ethical Treatment of Reinforcement Learners (PETRL) is an advocacy group that promotes the idea that certain machine learning algorithms may eventually possess sentience and therefore moral patienthood. One early exploration of this idea was a paper by Brian Tomasik of the Foundational Research Institute[1], which also introduced the name PETRL. Daswani and Leike[2] propose defining happiness for reinforcement learners as the difference between received and expected reward.

See also

References

  1. Do Artificial Reinforcement-Learning Agents Matter Morally?
  2. A Definition of Happiness for Reinforcement Learning Agents

External links