-
Notifications
You must be signed in to change notification settings - Fork 4
/
index.html
6 lines (4 loc) · 14.4 KB
/
index.html
1
2
3
4
5
6
<!doctype html> <html lang=en > <script async src="https://www.googletagmanager.com/gtag/js?id=UA-149861753-1"></script> <script> window.dataLayer = window.dataLayer || []; function gtag() { dataLayer.push(arguments); } gtag('js', new Date()); gtag('config', 'UA-149861753-1'); </script> <title>JuliaReinforcementLearning</title> <link rel=icon href="/assets/site/logo.svg"> <link rel=stylesheet href="/css/custom.css" /> <link rel=stylesheet href="https://stackpath.bootstrapcdn.com/bootstrap/4.5.0/css/bootstrap.min.css" integrity="sha384-9aIt2nRpC12Uk9gS9baDl411NQApFmC26EwAOH8WgZl5MYYxFfc+NcPb1dKGj7Sk" crossorigin=anonymous > <script async defer src="https://buttons.github.io/buttons.js"></script> <script src="https://code.jquery.com/jquery-3.5.1.slim.min.js" integrity="sha384-DfXdz2htPH0lsSSs5nCTpuj/zy4C+OGpamoFVy38MVBnE+IbbVYUew+OrCXaRkfj" crossorigin=anonymous ></script> <script src="https://cdn.jsdelivr.net/npm/popper.js@1.16.0/dist/umd/popper.min.js" integrity="sha384-Q6E9RHvbIyZFJoft+2mJbHaEWldlvI9IOYy5n3zV9zzTtmI3UksdQRVvoxMfooAo" crossorigin=anonymous ></script> <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.5.0/js/bootstrap.min.js" integrity="sha384-OgVRvuATP1z7JjHLkuOU7Xw704+h835Lr+6QL9UvYjZE3Ipu6Tp75j7Bh/kR0JKI" crossorigin=anonymous ></script> <nav class="navbar navbar-expand-lg navbar-dark fixed-top" style="background-color: #1fd1f9; background-image: linear-gradient(315deg, #1fd1f9 0%, #b621fe 74%); " id=mainNav > <div class=container > <button class=navbar-toggler type=button data-toggle=collapse data-target="#navbarTogglerDemo01" aria-controls=navbarTogglerDemo01 aria-expanded=false aria-label="Toggle navigation"> <span class=navbar-toggler-icon ></span> </button> <div class="collapse navbar-collapse" id=navbarTogglerDemo01 > <span class=navbar-brand > <a class=navbar-brand href="/"> JuliaReinforcementLearning </a> </span> <ul class="navbar-nav ml-auto"> <!-- <li class=nav-item > <a class=nav-link href="/get_started/">Get Started</a> --> <!-- <li class=nav-item > <a class=nav-link href="/guide/">Guide</a> <li class=nav-item > <a class=nav-link href="/contribute/">Contribute</a> --> <li class=nav-item > <a class=nav-link href="/docs/">Doc</a> <li class=nav-item > <a class=nav-link href="https://github.com/JuliaReinforcementLearning">Github</a> </ul> </div> </nav> <div class="jumbotron jumbotron-fluid page-heading text-center"> <div class=container > <img src="/assets/site/logo.svg" width=250px > <h1> ReinforcementLearning.jl </h1> <p class=text-muted > A collection of tools for doing reinforcement learning research in Julia. </p> <p> <a class=github-button href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl" data-icon=octicon-star data-size=large data-show-count=true aria-label="Star JuliaLang/julia on GitHub">Star Us</a> </p> </div> </div> <hr> <div class=container > <div class="row key-feature"> <div class=col-md-12 > <h3 class=text-muted >Key Features &<br>Capabilities</h3> </div> </div> <div class=row > <div class="col-lg-3 col-md-6 col-sm-12 key-feature-box"> <h5>Easy experimentation</h5> <p>Make it easy for new users to run benchmark experiments, compare different algorithms, evaluate and diagnose agents.</p> </div> <div class="col-lg-3 col-md-6 col-sm-12 key-feature-box"> <h5>Reproducibility</h5> <p>Facilitate reproducibility from traditional tabular methods to modern deep reinforcement learning algorithms.</p> </div> <div class="col-lg-3 col-md-6 col-sm-12 key-feature-box"> <h5>Reusability and extensibility</h5> <p>Provide elaborately designed components and interfaces to help users implement new algorithms.</p> </div> <div class="col-lg-3 col-md-6 col-sm-12 key-feature-box"> <h5>Feature-rich Environments</h5> <p>A number of built-in environments and third-party environment wrappers are provided to evaluate algorithms in various scenarios.</p> </div> </div> </div> <hr> <div class=container > <div class="row feature-section"> <div class="col-lg-7 col-md-6 "> <div class=row > <div class="col-lg-1 col-md-0"> </div> <div class="col-lg-10 col-md-12 text-center"> <h3>Get Started in 3 lines!</h3> <p>ReinforcementLearning.jl is a wrapper package which contains a collection of different packages in the JuliaReinforcementLearning organization. You can simply run many built-in experiments in 3 lines.</p> <a type=button href="https://juliareinforcementlearning.org/docs/#Get-Started" class="btn btn-sm btn-outline-secondary">Get Started!</a> </div> <div class="col-lg-1 col-md-0"> </div> </div> </div> <div class="col-lg-5 col-md-6 mt-auto mb-auto"> <div style="background: #272822; overflow:auto;width:auto;padding:.8em .8em;border-radius:15px"> <pre style="margin: 0; line-height: 125%"><span style="color: #06a313">julia></span> <span style="color: #f8f8f2">]</span> <span style="color: #f8f8f2">add</span> <span style="color: #f8f8f2">ReinforcementLearningExperiments</span>
<span style="color: #06a313">julia></span> <span style="color: #66d9ef">using</span> <span style="color: #f8f8f2">ReinforcementLearningExperiments</span>
<span style="color: #06a313">julia></span> <span style="color: #66d9ef">run</span><span style="color: #f8f8f2">(</span><span style="color: #ee18ee">E</span><span style="color: #e6db74">`JuliaRL_BasicDQN_CartPole`</span><span style="color: #f8f8f2">)</span>
</pre> </div> </div> </div> </div> <hr> <div class=container > <div class="row feature-section text-center"> <div class="col-lg-4 col-md-6"> <img src="/assets/site/RLIntro2Cover-min.jpg"> </div> <div class="col-lg-8 col-md-6 mt-auto mb-auto"> <div class=row > <div class="col-lg-1 col-md-0"></div> <div class="col-lg-10 col-md-12"> <h3> Tabular Reinforcement Learning </h3> <p> In ReinforcementLearningAnIntroduction.jl, we reproduced most figures in the famous book: <span style="font-style:italic">Reinforcement Learning: An Introduction (Second Edition)</span>. You can try those examples interactively online with the help of MyBinder and learn many tabular reinforcement learning algorithms. </p> <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearningAnIntroduction.jl" type=button class="btn btn-sm btn-outline-secondary">Learn Now!</a> </div> <div class="col-lg-1 col-md-0"></div> </div> </div> </div> </div> <hr> <div class=container > <div class="row feature-section text-center"> <div class="col-lg-8 col-md-6 mt-auto mb-auto"> <div class=row > <div class="col-lg-1 col-md-0"></div> <div class="col-lg-10 col-md-12"> <h3> Deep Reinforcement Learning </h3> <p> In ReinforcementLearningZoo.jl, many deep reinforcement learning algorithms are implemented, including DQN, C51, Rainbow, IQN, A2C, PPO, DDPG, etc. All algorithms are written in a composable way, which make them easy to read, understand and extend. </p> <a href="https://juliareinforcementlearning.org/docs/experiments/" type=button class="btn btn-sm btn-outline-secondary">Try Now!</a> </div> <div class="col-lg-1 col-md-0"></div> </div> </div> <div class="col-lg-4 col-md-6"> <img src="/assets/site/RLZoo.svg"> </div> </div> </div> <hr> <div class=container > <div class=row > <div class=col-md-12 > <h2>Community</h2> </div> <div class=col-md-12 > <p class=h2-subheadline >Join the Julia Reinforcement Learning community to learn, contribute, and get your questions answered.</p> </div> </div> <div class=row > <div class="col-lg-4 col-md-12"> <div class=card > <div class=card-body > <h5 class=card-title > <svg class="octicon octicon-mark-github v-align-middle" height=32 viewBox="0 0 16 16" version=1.1 width=32 aria-hidden=true > <path fill-rule=evenodd d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0016 8c0-4.42-3.58-8-8-8z"> </path> </svg> Github Issue/Pull Request</h5> <p class=card-text >Ask package usage questions, discuss designs and propose new features through github issues. Contributions through pull requests are warmly welcomed!</p> <a type=button href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/issues" class="btn btn-sm btn-outline-secondary">Create an issue!</a> <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl/pulls" type=button class="btn btn-sm btn-outline-secondary">Make a PR!</a> </div> </div> </div> <div class="col-lg-4 col-md-12"> <div class=card > <div class=card-body > <h5 class=card-title ><svg xmlns="http://www.w3.org/2000/svg" height=32 viewBox="0 -1 104 106"> <defs> <style> .cls-1 { fill: #231f20; } .cls-2 { fill: #fff9ae; } .cls-3 { fill: #00aeef; } .cls-4 { fill: #00a94f; } .cls-5 { fill: #f15d22; } .cls-6 { fill: #e31b23; } </style> </defs> <title>Discourse_logo</title> <g id=Layer_2 data-name="Layer 2"> <g id=Layer_3 data-name="Layer 3"> <path class=cls-1 d="M51.87,0C23.71,0,0,22.83,0,51c0,.91,0,52.81,0,52.81l51.86-.05c28.16,0,51-23.71,51-51.87S80,0,51.87,0Z" /> <path class=cls-2 d="M52.37,19.74A31.62,31.62,0,0,0,24.58,66.41l-5.72,18.4L39.4,80.17a31.61,31.61,0,1,0,13-60.43Z" /> <path class=cls-3 d="M77.45,32.12a31.6,31.6,0,0,1-38.05,48L18.86,84.82l20.91-2.47A31.6,31.6,0,0,0,77.45,32.12Z" /> <path class=cls-4 d="M71.63,26.29A31.6,31.6,0,0,1,38.8,78L18.86,84.82,39.4,80.17A31.6,31.6,0,0,0,71.63,26.29Z" /> <path class=cls-5 d="M26.47,67.11a31.61,31.61,0,0,1,51-35A31.61,31.61,0,0,0,24.58,66.41l-5.72,18.4Z" /> <path class=cls-6 d="M24.58,66.41A31.61,31.61,0,0,1,71.63,26.29a31.61,31.61,0,0,0-49,39.63l-3.76,18.9Z" /> </g> </g> </svg> Julia Discourse/Slack <svg height=32 enable-background="new 0 0 2447.6 2452.5" viewBox="0 0 2447.6 2452.5" xmlns="http://www.w3.org/2000/svg"> <g clip-rule=evenodd fill-rule=evenodd > <path d="m897.4 0c-135.3.1-244.8 109.9-244.7 245.2-.1 135.3 109.5 245.1 244.8 245.2h244.8v-245.1c.1-135.3-109.5-245.1-244.9-245.3.1 0 .1 0 0 0m0 654h-652.6c-135.3.1-244.9 109.9-244.8 245.2-.2 135.3 109.4 245.1 244.7 245.3h652.7c135.3-.1 244.9-109.9 244.8-245.2.1-135.4-109.5-245.2-244.8-245.3z" fill="#36c5f0" /> <path d="m2447.6 899.2c.1-135.3-109.5-245.1-244.8-245.2-135.3.1-244.9 109.9-244.8 245.2v245.3h244.8c135.3-.1 244.9-109.9 244.8-245.3zm-652.7 0v-654c.1-135.2-109.4-245-244.7-245.2-135.3.1-244.9 109.9-244.8 245.2v654c-.2 135.3 109.4 245.1 244.7 245.3 135.3-.1 244.9-109.9 244.8-245.3z" fill="#2eb67d" /> <path d="m1550.1 2452.5c135.3-.1 244.9-109.9 244.8-245.2.1-135.3-109.5-245.1-244.8-245.2h-244.8v245.2c-.1 135.2 109.5 245 244.8 245.2zm0-654.1h652.7c135.3-.1 244.9-109.9 244.8-245.2.2-135.3-109.4-245.1-244.7-245.3h-652.7c-135.3.1-244.9 109.9-244.8 245.2-.1 135.4 109.4 245.2 244.7 245.3z" fill="#ecb22e" /> <path d="m0 1553.2c-.1 135.3 109.5 245.1 244.8 245.2 135.3-.1 244.9-109.9 244.8-245.2v-245.2h-244.8c-135.3.1-244.9 109.9-244.8 245.2zm652.7 0v654c-.2 135.3 109.4 245.1 244.7 245.3 135.3-.1 244.9-109.9 244.8-245.2v-653.9c.2-135.3-109.4-245.1-244.7-245.3-135.4 0-244.9 109.8-244.8 245.1 0 0 0 .1 0 0" fill="#e01e5a" /> </g> </svg></h5> <p class=card-text >Ask general reinforcement learning related questions on Julia discourse in the #machinelearning domain, or on the Slack in #reinforcement-learnin channel.</p> <a href="https://discourse.julialang.org/c/domain/ML/24" type=button class="btn btn-sm btn-outline-secondary">Ask on Discourse!</a> <a href="https://julialang.org/slack/" type=button class="btn btn-sm btn-outline-secondary">Join Julia Slack!</a> </div> </div> </div> <div class="col-lg-4 col-md-12"> <div class=card > <div class=card-body > <h5 class=card-title > <svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" height=30 viewBox="0 0 325 300" version=1.1 > <g id=surface91 > <path style=" stroke:none;fill-rule:nonzero;fill:rgb(79.6%,23.5%,20%);fill-opacity:1;" d="M 150.898438 225 C 150.898438 266.421875 117.320312 300 75.898438 300 C 34.476562 300 0.898438 266.421875 0.898438 225 C 0.898438 183.578125 34.476562 150 75.898438 150 C 117.320312 150 150.898438 183.578125 150.898438 225 " /> <path style=" stroke:none;fill-rule:nonzero;fill:rgb(22%,59.6%,14.9%);fill-opacity:1;" d="M 237.5 75 C 237.5 116.421875 203.921875 150 162.5 150 C 121.078125 150 87.5 116.421875 87.5 75 C 87.5 33.578125 121.078125 0 162.5 0 C 203.921875 0 237.5 33.578125 237.5 75 " /> <path style=" stroke:none;fill-rule:nonzero;fill:rgb(58.4%,34.5%,69.8%);fill-opacity:1;" d="M 324.101562 225 C 324.101562 266.421875 290.523438 300 249.101562 300 C 207.679688 300 174.101562 266.421875 174.101562 225 C 174.101562 183.578125 207.679688 150 249.101562 150 C 290.523438 150 324.101562 183.578125 324.101562 225 " /> </g> </svg> Other Julia Packages</h5> <p class=card-text > <ul class=package-list > <li><a href="https://github.com/jonathan-laurent/AlphaZero.jl">AlphaZero.jl</a> <li><a href="https://github.com/JuliaPOMDP/DeepQLearning.jl">DeepQLearning.jl</a> <li><a href="https://github.com/mkschleg/DeepRL.jl">DeepRL.jl</a> <li><a href="https://github.com/JuliaML/Reinforce.jl">Reinforce.jl</a> </ul> </p> <a href="https://juliahub.com/ui/Packages?q=reinforce" type=button class="btn btn-sm btn-outline-secondary">Find more packages on JuliaHub!</a> </div> </div> </div> </div> </div> <d-appendix> </d-appendix> <div class="distill-site-nav distill-site-footer"> <div class=row > <div class=col-md-3 ></div> <div class=col-md-6 > <p>This website is built with <a href="https://github.com/tlienart/Franklin.jl">Franklin.jl</a> of the <a href="https://github.com/tlienart/DistillTemplate">DistillTemplate</a> (licensed under <a href="https://github.com/distillpub/template/blob/master/LICENSE">Apache License 2.0</a>) and <a href="https://github.com/JuliaDocs/Documenter.jl">Documenter.jl</a>. The <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl">source code</a> of this website is licensed under <a href="https://github.com/JuliaReinforcementLearning/JuliaReinforcementLearning.github.io/blob/master/LICENSE">MIT License</a>. The <a href="https://github.com/JuliaReinforcementLearning">JuliaReinforcementLearning</a> organization was first created by <a href="https://github.com/jbrea">Johanni Brea</a> and then co-maintained by <a href="https://github.com/findmyway">Jun Tian</a>. And we thank <a href="https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl#contributors-">all the contributors </a> .</p> </div> <div class=col-md-3 ></div> </div> </div>