RSS

Peo­ple for the Eth­i­cal Treat­ment of Re­in­force­ment Learners

TagLast edit: 8 Jun 2022 20:35 UTC by Leo

People for the Ethical Treatment of Reinforcement Learners (PETRL) is an organization focused on the welfare of AI agents.

History

PETRL was founded by Daniel Filan, Buck Shlegeris, Jan Leike, Mayank Daswani, and others. A paper by Brian Tomasik on the ethics of reinforcement-learning agents inspired the creation of PETRL.[1]

PETRL was most active from 2014 to 2015.

Further reading

Bostrom, Nick (2014) Superintelligence: Paths, Dangers, Strategies, Oxford: Oxford University Press.

Daswani, Mayank & Jan Leike (2015) A definition of happiness for reinforcement learning agents, arXiv:1505.04497 [Cs].

Schwitzgebel, Eric & Mara Garza (2015) A defense of the rights of artificial intelligences: defense of the rights of artificial intelligences, Midwest Studies In Philosophy, vol. 39, pp. 98–119.

van der Merwe, Matthew (2019) What ever happened to PETRL (People for the Ethical Treatment of Reinforcement Learners)?, Effective Altruism Forum, December 30.

External links

People for the Ethical Treatment of Reinforcement Learners. Official website.

Related entries

artificial intelligence | artificial sentience | mind crime

  1. ^

    Tomasik, Brian (2014) Do artificial reinforcement-learning agents matter morally?, arXiv:1410.8233 [Cs], p. 23.

The Im­por­tance of Ar­tifi­cial Sentience

Jamie_Harris3 Mar 2021 17:17 UTC
70 points
10 comments11 min readEA link
(www.sentienceinstitute.org)

[Question] What ever hap­pened to PETRL (Peo­ple for the Eth­i­cal Treat­ment of Re­in­force­ment Learn­ers)?

matthew.vandermerwe30 Dec 2019 17:28 UTC
32 points
4 comments1 min readEA link
No comments.