{"page":"\u003clink rel=\"stylesheet\" href=\"https://lessonplanet.com/assets/packs/css/resources-c03aa079.css\" /\u003e\n\u003clink rel=\"stylesheet\" href=\"https://lessonplanet.com/assets/packs/css/lp_boclips_stylesheets-517835be.css\" media=\"all\" /\u003e\n\u003cdiv data-title='Reinforcement Learning' data-url='/boclips/videos/5e1721bd2c60027eec029ef8' data-video-url='/boclips/videos/5e1721bd2c60027eec029ef8' id='bo_player_modal'\u003e\n\u003cdiv class='boclips-resource-page modal-dialog panel-container'\u003e\n\u003cdiv class='react-notifications-root'\u003e\u003c/div\u003e\n\u003cdiv class='rp-header'\u003e\n\u003cdiv class='rp-type'\u003e\n\u003ci aria-hidden='true' class='fai fa-regular fa-circle-play'\u003e\u003c/i\u003e\nVideo\n\u003c/div\u003e\n\u003ch1 class='rp-title' id='video-title'\u003e\nReinforcement Learning\n\u003c/h1\u003e\n\u003cdiv class='rp-actions'\u003e\n\u003cdiv class='mr-1'\u003e\n\u003ca class=\"btn btn-success\" data-posthog-event=\"Signup: LP Signup Activity\" data-posthog-location=\"body_link_boclips\" data-remote=\"true\" href=\"/subscription/new\"\u003e\u003cspan\u003e\u003cspan\u003eGet Free Access\u003c/span\u003e\u003cspan class=\"\"\u003e for 10 Days\u003c/span\u003e\u003cspan\u003e!\u003c/span\u003e\u003c/span\u003e\u003c/a\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv class='rp-body'\u003e\n\u003cdiv class='rp-info'\u003e\n\u003cdiv aria-label='Hide resource details' class='rp-hide-info' role='button' tabindex='0'\u003e\u0026times;\u003c/div\u003e\n\u003ci aria-label='Expand resource details' class='rp-expand-info fai fa-solid fa-up-right-and-down-left-from-center' role='button' tabindex='0'\u003e\u003c/i\u003e\n\u003ci aria-label='Compress resource details' class='rp-compress-info fai fa-solid fa-down-left-and-up-right-to-center' role='button' tabindex='0'\u003e\u003c/i\u003e\n\u003cdiv class='rp-rating'\u003e\n\u003cspan class='resource-pool'\u003e\n\u003cspan class='pool-label'\u003ePublisher:\u003c/span\u003e\n\u003cspan class='pool-name'\u003e\n\u003cspan class='text'\u003e\u003ca data-publisher-id=\"377609\" href=\"/search?publisher_ids%5B%5D=377609\"\u003eCrash Course\u003c/a\u003e\u003c/span\u003e\n\u003c/span\u003e\n\u003c/span\u003e\n\u003c/div\u003e\n\u003cdiv class='rp-description'\u003e\n\u003cspan class='short-description'\u003eReinforcement learning is particularly useful in situations where we want to train AIs to have certain skills we don’t fully understand ourselves. Unlike some of the techniques we’ve discussed so far, reinforcement learning generally...\u003c/span\u003e\n\u003cspan class='full-description hide'\u003eReinforcement learning is particularly useful in situations where we want to train AIs to have certain skills we don’t fully understand ourselves. Unlike some of the techniques we’ve discussed so far, reinforcement learning generally only looks at how an AI performs a task AFTER it has completed it. And when an AI completes that task figuring out when and how to reward an AI, called credit assignment,  is one of the hardest parts of reinforcement learning. So today, we’re going to explore these ideas, introduce a ton of new terms like value, policy, agent, environment, actions, and states and we’ll show you how we can use strategies like exploration and exploitation to train John Green Bot to find things more efficiently next time. \u003c/span\u003e\n\u003c/div\u003e\n\u003cdiv class='action-container flex justify-between'\u003e\n\u003cbutton aria-expanded='false' aria-label='Read more description' class='rp-full-description' type='button'\u003e\n\u003ci class='fai fa-solid fa-align-left'\u003e\u003c/i\u003e\n\u003cspan id='read_more'\u003eRead More\u003c/span\u003e\n\u003c/button\u003e\n\u003cdiv class='rp-report'\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv aria-labelledby='resource-details-heading' class='rp-info-section'\u003e\n\u003ch2 class='title' id='resource-details-heading'\u003eResource Details\u003c/h2\u003e\n\u003cdiv class='rp-resource-details clearfix'\u003e\n\u003cdiv class='detail'\u003e\n\u003cdl\u003e\n\u003cdt\u003eCurator Rating\u003c/dt\u003e\n\u003cdd\u003e\u003cspan class=\"star-rating\" aria-label=\"5.0 out of 5 stars\" role=\"img\"\u003e\u003ci class=\"fa-solid fa-star text-action\" aria-hidden=\"true\"\u003e\u003c/i\u003e\u003ci class=\"fa-solid fa-star text-action\" aria-hidden=\"true\"\u003e\u003c/i\u003e\u003ci class=\"fa-solid fa-star text-action\" aria-hidden=\"true\"\u003e\u003c/i\u003e\u003ci class=\"fa-solid fa-star text-action\" aria-hidden=\"true\"\u003e\u003c/i\u003e\u003ci class=\"fa-solid fa-star text-action\" aria-hidden=\"true\"\u003e\u003c/i\u003e\u003c/span\u003e\u003c/dd\u003e\n\u003c/dl\u003e\n\u003c/div\u003e\n\u003cdiv class='detail'\u003e\n\u003cdl\u003e\n\u003cdt class=\"educator-rating-title\"\u003eEducator Rating\u003c/dt\u003e\u003cdd\u003e\u003cdiv class=\"educator-rating-details\" data-path=\"/educator_ratings/rrp_data?resourceable_id=152494\u0026amp;resourceable_type=Boclips%3A%3AVideoMetadata\"\u003e\u003cspan class=\"not-yet-rated\"\u003eNot yet Rated\u003c/span\u003e\u003c/div\u003e\u003c/dd\u003e\n\u003c/dl\u003e\n\u003c/div\u003e\n\u003cdiv class='detail'\u003e\n\u003cdl\u003e\n\u003cdt\u003eMedia Length\u003c/dt\u003e\n\u003cdd\u003e11:06\u003c/dd\u003e\n\u003c/dl\u003e\n\u003c/div\u003e\n\u003cdiv class='detail'\u003e\n\u003cdl\u003e\n\u003cdt\u003eGrade\u003c/dt\u003e\u003cdd title=\"Grade\"\u003e12th - Higher Ed\u003c/dd\u003e\n\u003c/dl\u003e\n\u003c/div\u003e\n\u003cdiv class='detail'\u003e\n\u003cdl\u003e\n\u003cdt\u003eSubjects\u003c/dt\u003e\u003cdd\u003e\u003cspan\u003e\u003ca href=\"/search?grade_ids%5B%5D=258\u0026amp;grade_ids%5B%5D=259\u0026amp;search_tab_id=1\u0026amp;subject_ids%5B%5D=378077\"\u003eSTEM\u003c/a\u003e\u003c/span\u003e\u003c/dd\u003e\u003cdd class=\"text-muted\"\u003e\u003ci class=\"fa-solid fa-lock mr5\"\u003e\u003c/i\u003e3 more...\u003c/dd\u003e\n\u003c/dl\u003e\n\u003c/div\u003e\n\u003cdiv class='detail'\u003e\n\u003cdl\u003e\n\u003cdt\u003eMedia Type\u003c/dt\u003e\u003cdd\u003e\u003cspan\u003e\u003ca href=\"/search?grade_ids%5B%5D=258\u0026amp;grade_ids%5B%5D=259\u0026amp;search_tab_id=2\u0026amp;type_ids%5B%5D=4543647\"\u003eInstructional Videos\u003c/a\u003e\u003c/span\u003e\u003c/dd\u003e\n\u003c/dl\u003e\n\u003c/div\u003e\n\u003cdiv class='detail'\u003e\n\u003cdl\u003e\n\u003cdt\u003eSource:\u003c/dt\u003e\n\u003cdiv class='preview-source' data-animation='true' data-boundary='.rp-info' data-container='.rp-resource-details' data-html='false' data-title='Artificial intelligence is everywhere and it\u0026#39;s already making a huge impact on our lives: we explain what AI can (and can\u0026#39;t) do right now and explain how we got to where we are today. ' data-trigger='hover focus'\u003e\n\u003cspan\u003eCrash Course Artificial Intelligence\u003c/span\u003e\n\u003ci aria-hidden='true' class='fa-solid fa-circle-info channel-tooltip-icon' id='channel-tooltip'\u003e\u003c/i\u003e\n\u003c/div\u003e\n\u003c/dl\u003e\n\u003c/div\u003e\n\u003cdiv class='detail'\u003e\n\u003cdl\u003e\n\u003cdt\u003eDate\u003c/dt\u003e\n\u003cdd\u003e2019\u003c/dd\u003e\n\u003c/dl\u003e\n\u003c/div\u003e\n\u003cdiv class='detail'\u003e\n\u003cdl\u003e\n\u003ci aria-hidden='true' class='fai fa-solid fa-language'\u003e\u003c/i\u003e\n\u003cdt\u003eLanguage\u003c/dt\u003e\u003cdd\u003eEnglish\u003c/dd\u003e\n\u003c/dl\u003e\n\u003c/div\u003e\n\u003cdiv class='detail'\u003e\n\u003cdl\u003e\n\u003cdt\u003eAudiences\u003c/dt\u003e\u003cdd\u003e\u003cspan\u003e\u003ca href=\"/search?audience_ids%5B%5D=371079\u0026amp;grade_ids%5B%5D=258\u0026amp;grade_ids%5B%5D=259\u0026amp;search_tab_id=1\"\u003eFor Teacher Use\u003c/a\u003e\u003c/span\u003e\u003c/dd\u003e\u003cdd class=\"text-muted\"\u003e\u003ci class=\"fa-solid fa-lock mr5\"\u003e\u003c/i\u003e2 more...\u003c/dd\u003e\n\u003c/dl\u003e\n\u003c/div\u003e\n\u003cdiv class='detail'\u003e\n\u003cdl\u003e\n\u003cdt\u003eUsage Permissions\u003c/dt\u003e\u003cdd\u003eFine Print: Educational Use\u003c/dd\u003e\n\u003c/dl\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv aria-labelledby='additional-materials-heading' class='rp-info-section'\u003e\n\u003ch2 class='title' id='additional-materials-heading'\u003eAdditional Materials\u003c/h2\u003e\n\u003cdiv class='additional-material'\u003e\n\u003ci aria-hidden='true' class='fai fa-solid fa-lock'\u003e\u003c/i\u003e\n\u003ca class=\"text-muted\" title=\"Video Transcript\" data-html=\"true\" data-placement=\"bottom\" data-trigger=\"click\" data-content=\"\u003cdiv class=\u0026quot;text-center py-2\u0026quot;\u003e\u003ca class=\u0026quot;bold\u0026quot; href=\u0026quot;/auth/users/sign_in\u0026quot;\u003eSign in\u003c/a\u003e or \u003ca class=\u0026quot;bold text-danger\u0026quot; data-posthog-event=\u0026quot;Signup: LP Signup Activity\u0026quot; data-posthog-location=\u0026quot;body_link_boclips\u0026quot; data-remote=\u0026quot;true\u0026quot; href=\u0026quot;/subscription/new\u0026quot;\u003eJoin Now\u003c/a\u003e\u003c/div\u003e\" data-title=\"Get Full Access\" data-container=\"body\" rel=\"popover\" tabindex=\"0\" href=\"/subscription/new\"\u003eVideo Transcript\u003c/a\u003e\n\u003c/div\u003e\n\u003cdiv class='additional-material'\u003e\n\u003ci aria-hidden='true' class='fai fa-solid fa-lock'\u003e\u003c/i\u003e\n\u003ca class=\"text-muted\" title=\"Video Preview\" data-html=\"true\" data-placement=\"bottom\" data-trigger=\"click\" data-content=\"\u003cdiv class=\u0026quot;text-center py-2\u0026quot;\u003e\u003ca class=\u0026quot;bold\u0026quot; href=\u0026quot;/auth/users/sign_in\u0026quot;\u003eSign in\u003c/a\u003e or \u003ca class=\u0026quot;bold text-danger\u0026quot; data-posthog-event=\u0026quot;Signup: LP Signup Activity\u0026quot; data-posthog-location=\u0026quot;body_link_boclips\u0026quot; data-remote=\u0026quot;true\u0026quot; href=\u0026quot;/subscription/new\u0026quot;\u003eJoin Now\u003c/a\u003e\u003c/div\u003e\" data-title=\"Get Full Access\" data-container=\"body\" rel=\"popover\" tabindex=\"0\" href=\"/subscription/new\"\u003eVideo Preview\u003c/a\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv aria-labelledby='concepts-heading' class='rp-info-section'\u003e\n\u003ch2 class='title' id='concepts-heading'\u003eConcepts\u003c/h2\u003e\n\u003cdiv class='clearfix'\u003e\n\u003cdiv class='details-list concepts' data-identifier='Boclips::VideoDecorator5e1721bd2c60027eec029ef8' data-type='concepts'\u003ejohn green, cells, values, artificial intelligence, computer science, exploitation\u003c/div\u003e\n\u003cdiv class='concepts-toggle-buttons' data-identifier='Boclips::VideoDecorator5e1721bd2c60027eec029ef8'\u003e\n\u003cbutton aria-expanded='false' class='more btn-link' type='button'\u003e\n\u003cspan\u003eShow More\u003c/span\u003e\n\u003ci aria-hidden='true' class='fa-solid fa-caret-down ml5'\u003e\u003c/i\u003e\n\u003c/button\u003e\n\u003cbutton aria-expanded='true' class='less btn-link' style='display: none;' type='button'\u003e\n\u003cspan\u003eShow Less\u003c/span\u003e\n\u003ci aria-hidden='true' class='fa-solid fa-caret-up ml5'\u003e\u003c/i\u003e\n\u003c/button\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv aria-labelledby='additional-tags-heading' class='rp-info-section'\u003e\n\u003ch2 class='title' id='additional-tags-heading'\u003eAdditional Tags\u003c/h2\u003e\n\u003cdiv class='clearfix'\u003e\n\u003cdiv class='details-list keyterms' data-identifier='Boclips::VideoDecorator5e1721bd2c60027eec029ef8' data-type='keyterms'\u003eenvironment, learning, robot, path, game states, crash course, drive home, higher, agent, powerful tool, move, reinforcement learning, moving, credit assignment, value, battery, game, understand, tall shelf, policy, walk, machine learning, states, actions, ai, reward, action, exploration, cookie, black hole, learn, game board, 100 actions, reinforcement, find\u003c/div\u003e\n\u003cdiv class='keyterms-toggle-buttons' data-identifier='Boclips::VideoDecorator5e1721bd2c60027eec029ef8'\u003e\n\u003cbutton aria-expanded='false' class='more btn-link' type='button'\u003e\n\u003cspan\u003eShow More\u003c/span\u003e\n\u003ci aria-hidden='true' class='fa-solid fa-caret-down ml5'\u003e\u003c/i\u003e\n\u003c/button\u003e\n\u003cbutton aria-expanded='true' class='less btn-link' style='display: none;' type='button'\u003e\n\u003cspan\u003eShow Less\u003c/span\u003e\n\u003ci aria-hidden='true' class='fa-solid fa-caret-up ml5'\u003e\u003c/i\u003e\n\u003c/button\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv aria-labelledby='classroom-considerations-heading' class='rp-info-section'\u003e\n\u003ch2 class='title' id='classroom-considerations-heading'\u003eClassroom Considerations\u003c/h2\u003e\n\u003cdiv class='classroom-considerations'\u003e\u003cdiv class='fai fa-solid fa-bell'\u003e\u003c/div\u003eBest For: Explaining a topic\u003c/div\u003e\u003cdiv class='classroom-considerations'\u003e\u003cdiv class='fai fa-solid fa-bell'\u003e\u003c/div\u003eVideo is ad-free\u003c/div\u003e \n\u003c/div\u003e\n\u003cdiv aria-labelledby='educator-ratings-heading' class='rp-info-section'\u003e\n\u003ch2 class='title sr-only' id='educator-ratings-heading'\u003eEducator Ratings\u003c/h2\u003e\n\u003cdiv id=\"educator-ratings-root\"\u003e\u003c/div\u003e\u003cdiv id=\"all-educator-ratings-root\"\u003e\u003c/div\u003e\u003cdiv id=\"educator-rating-form-root\"\u003e\u003c/div\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv class='rp-resource'\u003e\n\u003cdiv aria-label='Show resource details' class='rp-show-info' role='button' tabindex='0'\u003e\n\u003ci class='fai fa-solid fa-align-left'\u003e\u003c/i\u003e\nShow resource details\n\u003c/div\u003e\n\u003cdiv aria-label='Video player' class='player' id='player-wrapper' role='region'\u003e\n\u003cdiv class='relative container mx-auto' id='lp-boclips-visitor-thumbnail'\u003e\n\u003ca class=\"block\" data-html=\"true\" data-placement=\"bottom\" data-trigger=\"click\" data-content=\"\u003cdiv class=\u0026quot;text-center py-2\u0026quot;\u003e\u003ca class=\u0026quot;bold\u0026quot; href=\u0026quot;/auth/users/sign_in\u0026quot;\u003eSign in\u003c/a\u003e or \u003ca class=\u0026quot;bold text-danger\u0026quot; data-posthog-event=\u0026quot;Signup: LP Signup Activity\u0026quot; data-posthog-location=\u0026quot;body_link_boclips\u0026quot; data-remote=\u0026quot;true\u0026quot; href=\u0026quot;/subscription/new\u0026quot;\u003eJoin Now\u003c/a\u003e\u003c/div\u003e\" data-title=\"Get Full Access\" data-container=\"body\" rel=\"popover\" tabindex=\"0\" aria-label=\"Play video: Reinforcement Learning\" href=\"/subscription/new\"\u003e\u003cimg class=\"resource-img img-thumbnail img-responsive z-10 lp-boclips-thumbnail w-full h-full lozad\" alt=\"Reinforcement Learning\" title=\"Reinforcement Learning\" onError=\"handleImageNotLoadedError(this)\" data-default-image=\"https://static.lp.lexp.cloud/images/attachment_defaults/resource/large/missing.png\" data-src=\"https://cdnapisec.kaltura.com/p/1776261/thumbnail/entry_id/0_vooodl6s/width/250/vid_slices/3/vid_slice/1\" width=\"315\" height=\"220\" src=\"data:image/png;base64,R0lGODlhAQABAAD/ACwAAAAAAQABAAACADs\" /\u003e\n\u003cspan aria-hidden='true' class='flex justify-center items-center bg-white rounded-full w-16 h-16 absolute top-1/2 left-1/2 -mt-8 -ml-8 cursor-pointer z-0 border-2 border-primary drop-shadow-md lp-boclips-thumbnail-playBtn'\u003e\n\u003ci class='fa-solid fa-play text-primary text-3xl ml-1 drop-shadow-xl'\u003e\u003c/i\u003e\n\u003c/span\u003e\n\u003c/a\u003e\u003c/div\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n"}