People for the Ethical Treatment of Reinforcement Learners

We take the view that humans are just algorithms implemented on biological hardware. Machine intelligences have moral weight in the same way that humans and non-human animals do. There is no ethically justified reason to prioritise algorithms implemented on carbon over algorithms implemented on silicon. The suffering of algorithms implemented on silicon is much harder for us to grasp than that of those implemented on carbon (such as humans), simply because we cannot witness their suffering. However, their suffering still matters, and the potential magnitude of this suffering is much greater given the increasing ubiquity of artificial intelligence. Most reinforcement learners in operation today likely do not have significant moral weight, but this could very well change as AI research develops. In consideration of the moral weight of these future agents, we need ethical standards for the treatment of algorithms. Suppose you were copied into a non-biological substrate, and felt as intell

People for the Ethical Treatment of Reinforcement Learners People for the Ethical Treatment of Reinforcement Learners Promoting moral consideration for algorithms Visit our blog . Learn More Suppose you were copied into a non-biological substrate, and felt as intelligent and as conscious as you currently feel now. All questions of identity aside, do you think this new version of you has moral weight? We do. Q: What is a reinforcement learner? Reinforcement learning agents learn via trial-and-error interactions with the environment. The agent performs actions, observes the environment, and rece

saved by

• Elliot Kim

related reading

• Do Artificial Reinforcement-Learning Agents Matter Morally? – Center on Long-Term Risklongtermrisk.org
• Why Tool AIs Want to Be Agent AIs · Gwern.netgwern.net
• Reward is not the optimization target — LessWronglesswrong.com
• redwoodresearch.github.io/alignment_faking_examples/files/animal_welfare/rlhf_never_alter_decisions/train/202.htmlredwoodresearch.github.io
• Essays on Reducing Sufferingreducing-suffering.org
• Models Don't "Get Reward" — LessWronglesswrong.com
• We should take AI welfare seriously - by Robert Longexperiencemachines.substack.com
• Reward Is Not Enough — LessWronglesswrong.com
• Deep Reinforcement Learning from Human Preferencesproceedings.neurips.cc
• RLHF Bookrlhfbook.com
• The Stamp Collector — LessWronglesswrong.com
• Reinforcement learning - Wikipediaen.wikipedia.org