Podcasts Technology Linear Digressions Reinforcement Learning Gone Wrong

Reinforcement Learning Gone Wrong

Published: July 11, 2016, 2:42 a.m.

Last week\u2019s episode on artificial intelligence gets a huge payoff this week\u2014we\u2019ll explore a wonderful couple of papers about all the ways that artificial intelligence can go wrong. Malevolent actors? You bet. Collateral damage? Of course. Reward hacking? Naturally! It\u2019s fun to think about, and the discussion starting now will have reverberations for decades to come.\n\nhttps://www.technologyreview.com/s/601519/how-to-create-a-malevolent-artificial-intelligence/\nhttp://arxiv.org/abs/1605.02817\nhttps://arxiv.org/abs/1606.06565