{"id":110787,"date":"2020-08-03T10:16:29","date_gmt":"2020-08-03T17:16:29","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2020\/08\/deepmind-releases-acme-a-distributed-framework-for-reinforcement-learning-algorithm-development"},"modified":"2020-08-03T10:16:29","modified_gmt":"2020-08-03T17:16:29","slug":"deepmind-releases-acme-a-distributed-framework-for-reinforcement-learning-algorithm-development","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2020\/08\/deepmind-releases-acme-a-distributed-framework-for-reinforcement-learning-algorithm-development","title":{"rendered":"DeepMind releases Acme, a distributed framework for reinforcement learning algorithm development"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/deepmind-releases-acme-a-distributed-framework-for-reinforcement-learning-algorithm-development.jpg\"><\/a><\/p>\n<p>DeepMind this week released <a href=\"https:\/\/github.com\/deepmind\/acme\">Acme<\/a>, a framework intended to simplify the development of <a href=\"https:\/\/venturebeat.com\/tag\/reinforcement-learning\">reinforcement learning<\/a> algorithms by enabling AI-driven agents to run at various scales of execution. According to the engineers and researchers behind Acme, who <a href=\"https:\/\/arxiv.org\/pdf\/2006.00979.pdf\">coauthored<\/a> a technical paper on the work, it can be used to create agents with greater parallelization than in previous approaches.<\/p>\n<p>Reinforcement learning involves agents that interact with an environment to generate their own training data, and it\u2019s led to breakthroughs in fields from video games and robotics to self-driving robo-taxis. Recent advances are partly attributable to increases in the <em>amount<\/em> of training data used, which has motivated the design of systems where agents interact with instances of an environment to quickly accumulate experience. This scaling from single-process prototypes of algorithms to distributed systems often requires a reimplementation of the agents in question, DeepMind asserts, which is where the Acme framework comes in.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>DeepMind this week released Acme, a framework intended to simplify the development of reinforcement learning algorithms by enabling AI-driven agents to run at various scales of execution. According to the engineers and researchers behind Acme, who coauthored a technical paper on the work, it can be used to create agents with greater parallelization than in [\u2026]<\/p>\n","protected":false},"author":513,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[41,6,1491],"tags":[],"class_list":["post-110787","post","type-post","status-publish","format-standard","hentry","category-information-science","category-robotics-ai","category-transportation"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/110787","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/513"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=110787"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/110787\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=110787"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=110787"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=110787"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}