{"id":5863,"date":"2022-08-27T06:29:21","date_gmt":"2022-08-27T06:29:21","guid":{"rendered":"https:\/\/www.aiproblog.com\/index.php\/2022\/08\/27\/on-the-expressivity-of-markov-reward\/"},"modified":"2022-08-27T06:29:21","modified_gmt":"2022-08-27T06:29:21","slug":"on-the-expressivity-of-markov-reward","status":"publish","type":"post","link":"https:\/\/www.aiproblog.com\/index.php\/2022\/08\/27\/on-the-expressivity-of-markov-reward\/","title":{"rendered":"On the Expressivity of Markov Reward"},"content":{"rendered":"<p>Author: <\/p>\n<div>Our main results prove that while reward can express many tasks, there exist instances of each task type that no Markov reward function can capture. We then provide a set of polynomial-time algorithms that construct a reward function which allows an agent to optimize tasks of each of these three types, and correctly determine when no such reward function exists.<\/div>\n<p><a href=\"https:\/\/www.deepmind.com\/blog\/on-the-expressivity-of-markov-reward\">Go to Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Author: Our main results prove that while reward can express many tasks, there exist instances of each task type that no Markov reward function can [&hellip;] <span class=\"read-more-link\"><a class=\"read-more\" href=\"https:\/\/www.aiproblog.com\/index.php\/2022\/08\/27\/on-the-expressivity-of-markov-reward\/\">Read More<\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":458,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_bbp_topic_count":0,"_bbp_reply_count":0,"_bbp_total_topic_count":0,"_bbp_total_reply_count":0,"_bbp_voice_count":0,"_bbp_anonymous_reply_count":0,"_bbp_topic_count_hidden":0,"_bbp_reply_count_hidden":0,"_bbp_forum_subforum_count":0,"footnotes":""},"categories":[24],"tags":[],"_links":{"self":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts\/5863"}],"collection":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/comments?post=5863"}],"version-history":[{"count":0,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts\/5863\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/media\/461"}],"wp:attachment":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/media?parent=5863"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/categories?post=5863"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/tags?post=5863"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}