![](\"https:\/\/i0.wp.com\/softwareengineeringdaily.com\/wp-content\/uploads\/2018\/06\/AI_square.png?resize=175%2C175&ssl=1\")
<\/p>\n<\/p>\n
Evolutionary algorithms can generate surprising, effective solutions to our problems. <\/span><\/p>\n Evolutionary algorithms are often let loose within a simulated environment. The algorithm is given a function to optimize for, and the engineers expect that algorithm to evolve a solution that optimizes for the objective function given the constraints of the simulated environment. But sometimes these results are not exactly what we are looking for.<\/span><\/p>\n For example, imagine an evolutionary algorithm that tries to evolve a creature that does a flip within a simulated physics engine that mirrors the real world. <\/span><\/p>\n You could imagine all sorts of evolutionary traits. Maybe the creature will evolve to have legs that are like springs, and let the creature jump high enough to do a flip. Maybe the creature will develop normal legs with strong muscles that propel the creature high enough to flip. But you wouldn\u2019t expect the creature to evolve to be extremely tall–so tall that the creature can merely lean over fast enough so that the top of its body flips upside down. In one experiment, this is exactly what happened.<\/span><\/p>\n In another, similar experiment, the evolving creature discovered a bug in the physics engine of the simulated environment. This creature was able to exploit the problem with this physics engine to be able to move in ways that would not be possible in our real-world physical universe.<\/span><\/p>\n Evolutionary algorithms sometimes evolve solutions in ways that we don\u2019t expect. Researchers usually throw those results away, because they don\u2019t contribute to the result that the researchers are looking for. The consequence is that lots of interesting anecdotes get lost.<\/span><\/p>\n Joel Lehman, Dusan Misevic, and Jeff Clune are the lead authors of the paper \u201cT<\/span>he Surprising Creativity of Digital Evolution.\u201d The paper was a collection of anecdotes about strange results within the world of digital evolution. They join the show to describe what digital evolution is and some of the strange results that they surveyed in their paper.<\/span><\/p>\n Joel and Jeff are engineers at Uber\u2019s artificial intelligence division–so this topic has applicable importance to them. Machine learning is all about evolution within simulated environments, and developing safe algorithms for AI requires an understanding of what can go wrong in a poorly defined evolutionary system.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":" Evolutionary algorithms can generate surprising, effective solutions to our problems. Evolutionary algorithms are often let loose within a simulated environment. The algorithm is given a function to optimize for, and the engineers expect that algorithm to evolve a solution that optimizes for the objective function given the constraints of the simulated environment. But sometimes these<\/p>\n","protected":false},"author":3,"featured_media":5202,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_mi_skip_tracking":false,"_exactmetrics_sitenote_active":false,"_exactmetrics_sitenote_note":"","_exactmetrics_sitenote_category":0,"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_newsletter_tier_id":0,"footnotes":"","jetpack_publicize_message":"[podcast] Digital Evolution with Joel Lehman, Dusan Misevic, and @JeffClune @Uber @joelbot3000 #AI #ML #EvolutionaryAlgorithms","jetpack_is_tweetstorm":false,"jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","enabled":false}}},"categories":[1363,1080,14],"tags":[518,2178,2181,2179,2177,311,2180,40],"jetpack_publicize_connections":[],"acf":[],"yoast_head":"\n