Reinforcement Learning

بواسطة: Brilliant

Overview

This course was written by Tessa van der Heiden, a researcher and developer of autonomous driving algorithms at BMW.

In this course, you'll learn the mathematical underpinnings of reinforcement learning, a foundational machine learning technique in which an agent (or algorithm) is trained by trial and error. By rewarding the agent for good outcomes, it "learns" optimal strategies, which can be applied to problems in domains like robotics, quantitative trading, and game theory.
This course is intended for young professionals who are interested in applying machine learning techniques for decision making, or students who are pursuing a machine learning career or preparing for interviews.

Syllabus

  • Introduction:
    • Introduction: How does a computer devise a strategy to play a game optimally?
  • Foundations:
    • Value Functions: When transitioning between various options, the algorithm must quantify how good these options are.
    • Dynamic Programming: Optimize an interconnected system by reducing it into smaller systems.
    • Monte Carlo: If we make random moves a large number of times, we might notice a pattern that allows us to solve the problem deterministically.
  • Extensions:
    • Temporal Difference Learning: Explore a method of reinforcement learning that updates every time step — not just at the end of the episode.
    • Policy Gradient Methods: These methods take a different approach — by learning the optimal policy directly.
Reinforcement Learning
الذهاب الي الدورة

Reinforcement Learning

بواسطة: Brilliant

  • Brilliant
  • مدفوعة
  • الإنجليزية
  • متاح شهادة
  • أيام محددة
  • beginner
  • N/A
8.1.2PHP Version1.02sRequest Duration2MBMemory UsageGET ar/الدورات/{slug}Route
    • Booting (582ms)
    • Application (436ms)
    • 1 x Booting (57.06%)
      581.83ms
      1 x Application (42.72%)
      435.57ms
      14 templates were rendered
      • public.courses.show (resources/views/public/courses/show.blade.php)3bladefile
        Params
        0
        course
        1
        links
        2
        config
      • public.courses.partials.breadcrumbs (resources/views/public/courses/partials/breadcrumbs.blade.php)6bladefile
        Params
        0
        __env
        1
        app
        2
        errors
        3
        course
        4
        links
        5
        config
      • public.courses.partials.heading (resources/views/public/courses/partials/heading.blade.php)7bladefile
        Params
        0
        __env
        1
        app
        2
        errors
        3
        course
        4
        links
        5
        config
        6
        classes
      • public.courses.partials.details (resources/views/public/courses/partials/details.blade.php)6bladefile
        Params
        0
        __env
        1
        app
        2
        errors
        3
        course
        4
        links
        5
        config
      • public.courses.partials.breadcrumbs (resources/views/public/courses/partials/breadcrumbs.blade.php)6bladefile
        Params
        0
        __env
        1
        app
        2
        errors
        3
        course
        4
        links
        5
        config
      • public.courses.partials.heading (resources/views/public/courses/partials/heading.blade.php)7bladefile
        Params
        0
        __env
        1
        app
        2
        errors
        3
        course
        4
        links
        5
        config
        6
        classes
      • public.layouts.main (resources/views/public/layouts/main.blade.php)6bladefile
        Params
        0
        __env
        1
        app
        2
        errors
        3
        course
        4
        links
        5
        config
      • public.layouts.partials.meta (resources/views/public/layouts/partials/meta.blade.php)6bladefile
        Params
        0
        __env
        1
        app
        2
        errors
        3
        course
        4
        links
        5
        config
      • public.layouts.partials.navbar (resources/views/public/layouts/partials/navbar.blade.php)6bladefile
        Params
        0
        __env
        1
        app
        2
        errors
        3
        course
        4
        links
        5
        config
      • public.auth.profile.partials.links (resources/views/public/auth/profile/partials/links.blade.php)6bladefile
        Params
        0
        __env
        1
        app
        2
        errors
        3
        course
        4
        links
        5
        config
      • public.auth.profile.partials.link (resources/views/public/auth/profile/partials/link.blade.php)8bladefile
        Params
        0
        __env
        1
        app
        2
        errors
        3
        course
        4
        links
        5
        config
        6
        route
        7
        title
      • public.auth.profile.partials.link (resources/views/public/auth/profile/partials/link.blade.php)8bladefile
        Params
        0
        __env
        1
        app
        2
        errors
        3
        course
        4
        links
        5
        config
        6
        route
        7
        title
      • public.auth.profile.partials.link (resources/views/public/auth/profile/partials/link.blade.php)8bladefile
        Params
        0
        __env
        1
        app
        2
        errors
        3
        course
        4
        links
        5
        config
        6
        route
        7
        title
      • public.layouts.partials.flash-session (resources/views/public/layouts/partials/flash-session.blade.php)6bladefile
        Params
        0
        __env
        1
        app
        2
        errors
        3
        course
        4
        links
        5
        config
      uri
      GET ar/الدورات/{slug}
      middleware
      web, localize:ar
      controller
      App\Http\Controllers\CourseController@show
      as
      ar.courses.show
      namespace
      prefix
      /ar
      where
      file
      app/Http/Controllers/CourseController.php:17-35
      6 statements were executed123ms
      • select * from `courses` where `slug_ar` = 'reinforcement-learningm9H' limit 1
        8.33ms/app/Http/Controllers/CourseController.php:20corspedia
        Metadata
        Bindings
        • 0. reinforcement-learningm9H
        Backtrace
        • 17. /app/Http/Controllers/CourseController.php:20
        • 18. /vendor/laravel/framework/src/Illuminate/Routing/Controller.php:54
        • 19. /vendor/laravel/framework/src/Illuminate/Routing/ControllerDispatcher.php:43
        • 20. /vendor/laravel/framework/src/Illuminate/Routing/Route.php:260
        • 21. /vendor/laravel/framework/src/Illuminate/Routing/Route.php:205
      • update `courses` set `visitors` = `visitors` + 1, `courses`.`updated_at` = '2025-06-10 03:24:42' where `id` = 2325
        114ms/app/Http/Controllers/CourseController.php:21corspedia
        Metadata
        Bindings
        • 0. 2025-06-10 03:24:42
        • 1. 2325
        Backtrace
        • 17. /app/Http/Controllers/CourseController.php:21
        • 18. /vendor/laravel/framework/src/Illuminate/Routing/Controller.php:54
        • 19. /vendor/laravel/framework/src/Illuminate/Routing/ControllerDispatcher.php:43
        • 20. /vendor/laravel/framework/src/Illuminate/Routing/Route.php:260
        • 21. /vendor/laravel/framework/src/Illuminate/Routing/Route.php:205
      • select `id`, `name_en`, `name_ar`, `topic_id`, `slug_en`, `slug_ar` from `subjects` where `subjects`.`id` in (4)
        300μs/app/Http/Controllers/CourseController.php:23corspedia
        Metadata
        Backtrace
        • 20. /app/Http/Controllers/CourseController.php:23
        • 21. /vendor/laravel/framework/src/Illuminate/Routing/Controller.php:54
        • 22. /vendor/laravel/framework/src/Illuminate/Routing/ControllerDispatcher.php:43
        • 23. /vendor/laravel/framework/src/Illuminate/Routing/Route.php:260
        • 24. /vendor/laravel/framework/src/Illuminate/Routing/Route.php:205
      • select `id`, `name_en`, `name_ar`, `slug_en`, `slug_ar` from `topics` where `topics`.`id` in (1)
        230μs/app/Http/Controllers/CourseController.php:23corspedia
        Metadata
        Backtrace
        • 25. /app/Http/Controllers/CourseController.php:23
        • 26. /vendor/laravel/framework/src/Illuminate/Routing/Controller.php:54
        • 27. /vendor/laravel/framework/src/Illuminate/Routing/ControllerDispatcher.php:43
        • 28. /vendor/laravel/framework/src/Illuminate/Routing/Route.php:260
        • 29. /vendor/laravel/framework/src/Illuminate/Routing/Route.php:205
      • select * from `providers` where `providers`.`id` in (40) and `providers`.`deleted_at` is null
        270μs/app/Http/Controllers/CourseController.php:23corspedia
        Metadata
        Backtrace
        • 20. /app/Http/Controllers/CourseController.php:23
        • 21. /vendor/laravel/framework/src/Illuminate/Routing/Controller.php:54
        • 22. /vendor/laravel/framework/src/Illuminate/Routing/ControllerDispatcher.php:43
        • 23. /vendor/laravel/framework/src/Illuminate/Routing/Route.php:260
        • 24. /vendor/laravel/framework/src/Illuminate/Routing/Route.php:205
      • select * from `html_files` where `html_files`.`id` = 2316 limit 1
        300μs/app/Models/Course.php:84corspedia
        Metadata
        Bindings
        • 0. 2316
        Backtrace
        • 21. /app/Models/Course.php:84
        • 28. view::public.courses.show:29
        • 30. /vendor/laravel/framework/src/Illuminate/Filesystem/Filesystem.php:125
        • 31. /vendor/laravel/framework/src/Illuminate/View/Engines/PhpEngine.php:58
        • 32. /vendor/laravel/framework/src/Illuminate/View/Engines/CompilerEngine.php:72
      App\Models\HtmlFile
      1
      App\Models\Provider
      1
      App\Models\Topic
      1
      App\Models\Subject
      1
      App\Models\Course
      1
        _token
        YzhczAebkVYhFYuEAAEx7U6pYm19mV37w1GqacVY
        locale
        ar
        _previous
        array:1 [ "url" => "https://www.corspedia.com/ar/%D8%A7%D9%84%D8%AF%D9%88%D8%B1%D8%A7%D8%AA/reinfo...
        _flash
        array:2 [ "old" => [] "new" => [] ]
        PHPDEBUGBAR_STACK_DATA
        []
        path_info
        /ar/%D8%A7%D9%84%D8%AF%D9%88%D8%B1%D8%A7%D8%AA/reinforcement-learningm9H
        status_code
        200
        
        status_text
        OK
        format
        html
        content_type
        text/html; charset=UTF-8
        request_query
        []
        
        request_request
        []
        
        request_headers
        0 of 0
        array:24 [ "cf-ipcountry" => array:1 [ 0 => "US" ] "cf-connecting-ip" => array:1 [ 0 => "216.73.216.125" ] "cdn-loop" => array:1 [ 0 => "cloudflare; loops=1" ] "x-forwarded-proto" => array:1 [ 0 => "https" ] "x-forwarded-for" => array:1 [ 0 => "216.73.216.125" ] "sec-fetch-site" => array:1 [ 0 => "none" ] "accept" => array:1 [ 0 => "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7" ] "user-agent" => array:1 [ 0 => "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)" ] "upgrade-insecure-requests" => array:1 [ 0 => "1" ] "sec-ch-ua-platform" => array:1 [ 0 => ""Windows"" ] "sec-ch-ua-mobile" => array:1 [ 0 => "?0" ] "sec-ch-ua" => array:1 [ 0 => ""Chromium";v="130", "HeadlessChrome";v="130", "Not?A_Brand";v="99"" ] "cache-control" => array:1 [ 0 => "no-cache" ] "pragma" => array:1 [ 0 => "no-cache" ] "sec-fetch-dest" => array:1 [ 0 => "document" ] "cf-ray" => array:1 [ 0 => "94d5c1d56e69eada-ORD" ] "accept-encoding" => array:1 [ 0 => "gzip, br" ] "priority" => array:1 [ 0 => "u=0, i" ] "sec-fetch-user" => array:1 [ 0 => "?1" ] "sec-fetch-mode" => array:1 [ 0 => "navigate" ] "cf-visitor" => array:1 [ 0 => "{"scheme":"https"}" ] "host" => array:1 [ 0 => "www.corspedia.com" ] "content-length" => array:1 [ 0 => "" ] "content-type" => array:1 [ 0 => "" ] ]
        request_server
        0 of 0
        array:50 [ "USER" => "www-data" "HOME" => "/var/www" "HTTP_CF_IPCOUNTRY" => "US" "HTTP_CF_CONNECTING_IP" => "216.73.216.125" "HTTP_CDN_LOOP" => "cloudflare; loops=1" "HTTP_X_FORWARDED_PROTO" => "https" "HTTP_X_FORWARDED_FOR" => "216.73.216.125" "HTTP_SEC_FETCH_SITE" => "none" "HTTP_ACCEPT" => "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7" "HTTP_USER_AGENT" => "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)" "HTTP_UPGRADE_INSECURE_REQUESTS" => "1" "HTTP_SEC_CH_UA_PLATFORM" => ""Windows"" "HTTP_SEC_CH_UA_MOBILE" => "?0" "HTTP_SEC_CH_UA" => ""Chromium";v="130", "HeadlessChrome";v="130", "Not?A_Brand";v="99"" "HTTP_CACHE_CONTROL" => "no-cache" "HTTP_PRAGMA" => "no-cache" "HTTP_SEC_FETCH_DEST" => "document" "HTTP_CF_RAY" => "94d5c1d56e69eada-ORD" "HTTP_ACCEPT_ENCODING" => "gzip, br" "HTTP_PRIORITY" => "u=0, i" "HTTP_SEC_FETCH_USER" => "?1" "HTTP_SEC_FETCH_MODE" => "navigate" "HTTP_CF_VISITOR" => "{"scheme":"https"}" "HTTP_HOST" => "www.corspedia.com" "REDIRECT_STATUS" => "200" "SERVER_NAME" => "corspedia.com" "SERVER_PORT" => "443" "SERVER_ADDR" => "141.95.147.152" "REMOTE_USER" => "" "REMOTE_PORT" => "58040" "REMOTE_ADDR" => "172.70.126.34" "SERVER_SOFTWARE" => "nginx/1.18.0" "GATEWAY_INTERFACE" => "CGI/1.1" "HTTPS" => "on" "REQUEST_SCHEME" => "https" "SERVER_PROTOCOL" => "HTTP/2.0" "DOCUMENT_ROOT" => "/var/www/corspedia/public" "DOCUMENT_URI" => "/index.php" "REQUEST_URI" => "/ar/%D8%A7%D9%84%D8%AF%D9%88%D8%B1%D8%A7%D8%AA/reinforcement-learningm9H" "SCRIPT_NAME" => "/index.php" "CONTENT_LENGTH" => "" "CONTENT_TYPE" => "" "REQUEST_METHOD" => "GET" "QUERY_STRING" => "" "SCRIPT_FILENAME" => "/var/www/corspedia/public/index.php" "PATH_INFO" => "" "FCGI_ROLE" => "RESPONDER" "PHP_SELF" => "/index.php" "REQUEST_TIME_FLOAT" => 1749525881.4628 "REQUEST_TIME" => 1749525881 ]
        request_cookies
        []
        
        response_headers
        0 of 0
        array:5 [ "content-type" => array:1 [ 0 => "text/html; charset=UTF-8" ] "cache-control" => array:1 [ 0 => "no-cache, private" ] "date" => array:1 [ 0 => "Tue, 10 Jun 2025 03:24:42 GMT" ] "set-cookie" => array:2 [ 0 => "XSRF-TOKEN=eyJpdiI6InpyLzB6V2I0VnVSQ0tzZVJYM2dHbnc9PSIsInZhbHVlIjoiUUs4SkQ2eGpxV2NNZWVvU2JmeEhOWW9yMVhRQjhNVHZNWXY0b2tFUVZ4WGpQbVU1ZFVJQTdaRkNJSWUwM3M0T3J2VzhiWVBNcmZBU0hYYWlHdlU4RXNncjk2cUVmL202b0VwNW9rdDdoVEtjd0ROSUZSc0QwN1dxRU00c29wSnYiLCJtYWMiOiI1ZjJhMWI3MjEzMzYwZmEwMGU0ZDk5NTdhOTJjZDZlNjg0Zjg5OWZiNGI0YTQ2OGM4YWUxYTUxNDhhZTQxNmViIiwidGFnIjoiIn0%3D; expires=Tue, 10 Jun 2025 05:24:42 GMT; Max-Age=7200; path=/; samesite=laxXSRF-TOKEN=eyJpdiI6InpyLzB6V2I0VnVSQ0tzZVJYM2dHbnc9PSIsInZhbHVlIjoiUUs4SkQ2eGpxV2NNZWVvU2JmeEhOWW9yMVhRQjhNVHZNWXY0b2tFUVZ4WGpQbVU1ZFVJQTdaRkNJSWUwM3M0T3J2VzhiW" 1 => "laravel_session=eyJpdiI6IlVkVGtvODcyVVJsWHduUTY3TTZRZlE9PSIsInZhbHVlIjoidnBDS0dSWU9zREV2N2creW9EVUxhdFpESCt5eXRRNHlESk1hOGVTZ2dKV213RjRIaWY3dkxLdGNka2twTEJnN0lLaG00TTY3OHk4WXB0eVMrYlR3eU16SkVCcHEwUUFETVNSNkdWUUxINWo4cnhZY0h4aWdKb0dRcFBHNUoyL0QiLCJtYWMiOiI4ZjNhMjk5ZDgzOTViODczZTQ0Y2YyYjhlZDZmZWY4YTMwYjM3MTJhMmY3ZTMzMmY2MGM5YzMzNTkwNjY4NmY3IiwidGFnIjoiIn0%3D; expires=Tue, 10 Jun 2025 05:24:42 GMT; Max-Age=7200; path=/; httponly; samesite=laxlaravel_session=eyJpdiI6IlVkVGtvODcyVVJsWHduUTY3TTZRZlE9PSIsInZhbHVlIjoidnBDS0dSWU9zREV2N2creW9EVUxhdFpESCt5eXRRNHlESk1hOGVTZ2dKV213RjRIaWY3dkxLdGNka2twTEJnN0lL" ] "Set-Cookie" => array:2 [ 0 => "XSRF-TOKEN=eyJpdiI6InpyLzB6V2I0VnVSQ0tzZVJYM2dHbnc9PSIsInZhbHVlIjoiUUs4SkQ2eGpxV2NNZWVvU2JmeEhOWW9yMVhRQjhNVHZNWXY0b2tFUVZ4WGpQbVU1ZFVJQTdaRkNJSWUwM3M0T3J2VzhiWVBNcmZBU0hYYWlHdlU4RXNncjk2cUVmL202b0VwNW9rdDdoVEtjd0ROSUZSc0QwN1dxRU00c29wSnYiLCJtYWMiOiI1ZjJhMWI3MjEzMzYwZmEwMGU0ZDk5NTdhOTJjZDZlNjg0Zjg5OWZiNGI0YTQ2OGM4YWUxYTUxNDhhZTQxNmViIiwidGFnIjoiIn0%3D; expires=Tue, 10-Jun-2025 05:24:42 GMT; path=/XSRF-TOKEN=eyJpdiI6InpyLzB6V2I0VnVSQ0tzZVJYM2dHbnc9PSIsInZhbHVlIjoiUUs4SkQ2eGpxV2NNZWVvU2JmeEhOWW9yMVhRQjhNVHZNWXY0b2tFUVZ4WGpQbVU1ZFVJQTdaRkNJSWUwM3M0T3J2VzhiW" 1 => "laravel_session=eyJpdiI6IlVkVGtvODcyVVJsWHduUTY3TTZRZlE9PSIsInZhbHVlIjoidnBDS0dSWU9zREV2N2creW9EVUxhdFpESCt5eXRRNHlESk1hOGVTZ2dKV213RjRIaWY3dkxLdGNka2twTEJnN0lLaG00TTY3OHk4WXB0eVMrYlR3eU16SkVCcHEwUUFETVNSNkdWUUxINWo4cnhZY0h4aWdKb0dRcFBHNUoyL0QiLCJtYWMiOiI4ZjNhMjk5ZDgzOTViODczZTQ0Y2YyYjhlZDZmZWY4YTMwYjM3MTJhMmY3ZTMzMmY2MGM5YzMzNTkwNjY4NmY3IiwidGFnIjoiIn0%3D; expires=Tue, 10-Jun-2025 05:24:42 GMT; path=/; httponlylaravel_session=eyJpdiI6IlVkVGtvODcyVVJsWHduUTY3TTZRZlE9PSIsInZhbHVlIjoidnBDS0dSWU9zREV2N2creW9EVUxhdFpESCt5eXRRNHlESk1hOGVTZ2dKV213RjRIaWY3dkxLdGNka2twTEJnN0lL" ] ]
        session_attributes
        0 of 0
        array:5 [ "_token" => "YzhczAebkVYhFYuEAAEx7U6pYm19mV37w1GqacVY" "locale" => "ar" "_previous" => array:1 [ "url" => "https://www.corspedia.com/ar/%D8%A7%D9%84%D8%AF%D9%88%D8%B1%D8%A7%D8%AA/reinforcement-learningm9H" ] "_flash" => array:2 [ "old" => [] "new" => [] ] "PHPDEBUGBAR_STACK_DATA" => [] ]