lingo.lol is one of the many independent Mastodon servers you can use to participate in the fediverse.
A place for linguists, philologists, and other lovers of languages.

Server stats:

66
active users

#reinforcementlearning

0 posts0 participants0 posts today
Assn for Computing Machinery<p>"Intelligence is figuring out how the world works rather than waiting for someone to tell you how the world works."</p><p>Join us as we hear from Andrew Barto and Richard Sutton, the 2024 <a href="https://mastodon.acm.org/tags/ACMTuringAward" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ACMTuringAward</span></a> recipients as they discuss their work on <a href="https://mastodon.acm.org/tags/ReinforcementLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ReinforcementLearning</span></a>.</p><p><a href="https://vimeo.com/1085726612" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">vimeo.com/1085726612</span><span class="invisible"></span></a></p>
Python Weekly 🐍<p>This Python class offers a multiprocessing-powered Pool for efficiently collecting and managing experience replay data in reinforcement learning.</p><p><a href="https://github.com/NoteDance/Pool" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">github.com/NoteDance/Pool</span><span class="invisible"></span></a></p><p>Discussions: <a href="https://discu.eu/q/https://github.com/NoteDance/Pool" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">discu.eu/q/https://github.com/</span><span class="invisible">NoteDance/Pool</span></a></p><p><a href="https://mastodon.social/tags/programming" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>programming</span></a> <a href="https://mastodon.social/tags/python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>python</span></a> <a href="https://mastodon.social/tags/reinforcementlearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reinforcementlearning</span></a></p>
Dr. Carlotta A. Berry, PhD<p><a href="https://blacktwitter.io/tags/BlackInRobotics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BlackInRobotics</span></a> workshop series <a href="https://blacktwitter.io/tags/ROS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ROS</span></a> <a href="https://blacktwitter.io/tags/ROS2" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ROS2</span></a> <a href="https://blacktwitter.io/tags/Robot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Robot</span></a> <a href="https://blacktwitter.io/tags/Robotics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Robotics</span></a> <a href="https://blacktwitter.io/tags/STEM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>STEM</span></a> <a href="https://blacktwitter.io/tags/STEAM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>STEAM</span></a> <a href="https://blacktwitter.io/tags/BlackSTEM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BlackSTEM</span></a> <a href="https://blacktwitter.io/tags/BlackSTEAM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BlackSTEAM</span></a> <a href="https://blacktwitter.io/tags/Drone" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Drone</span></a> <a href="https://blacktwitter.io/tags/ComputerVision" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ComputerVision</span></a> <a href="https://blacktwitter.io/tags/Drones" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Drones</span></a> <a href="https://blacktwitter.io/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://blacktwitter.io/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://blacktwitter.io/tags/Neuralnetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Neuralnetworks</span></a> <a href="https://blacktwitter.io/tags/ReinforcementLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ReinforcementLearning</span></a> <a href="https://blacktwitter.io/tags/Learning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Learning</span></a></p>
Dr. Carlotta A. Berry, PhD<p><a href="https://blacktwitter.io/tags/BlackInRobotics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BlackInRobotics</span></a> workshop series <a href="https://blacktwitter.io/tags/ROS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ROS</span></a> <a href="https://blacktwitter.io/tags/ROS2" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ROS2</span></a> <a href="https://blacktwitter.io/tags/Robot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Robot</span></a> <a href="https://blacktwitter.io/tags/Robotics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Robotics</span></a> <a href="https://blacktwitter.io/tags/STEM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>STEM</span></a> <a href="https://blacktwitter.io/tags/STEAM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>STEAM</span></a> <a href="https://blacktwitter.io/tags/BlackSTEM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BlackSTEM</span></a> <a href="https://blacktwitter.io/tags/BlackSTEAM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BlackSTEAM</span></a> <a href="https://blacktwitter.io/tags/Drone" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Drone</span></a> <a href="https://blacktwitter.io/tags/ComputerVision" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ComputerVision</span></a> <a href="https://blacktwitter.io/tags/Drones" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Drones</span></a> <a href="https://blacktwitter.io/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://blacktwitter.io/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://blacktwitter.io/tags/Neuralnetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Neuralnetworks</span></a> <a href="https://blacktwitter.io/tags/ReinforcementLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ReinforcementLearning</span></a> <a href="https://blacktwitter.io/tags/Learning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Learning</span></a></p>
JesseTong<p><span class="h-card" translate="no"><a href="https://mastodon.gamedev.place/@lianna" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>lianna</span></a></span> Well, most <a href="https://mastodon.world/tags/AIs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AIs</span></a> and <a href="https://mastodon.world/tags/robots" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>robots</span></a> in fiction I think their inputs are mostly or fully sensory-based, and they learn in real time through <a href="https://mastodon.world/tags/ReinforcementLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ReinforcementLearning</span></a> - esque techniques. AIs like LLMs are frozen in place (they never update and are just replaced over time), and they do not have any meanful interaction to the real world, nor like reflection.</p><p>I'd think that robots like <a href="https://mastodon.world/tags/Sophia" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Sophia</span></a> a few years ago would be more closer to the former than the latter, but <a href="https://mastodon.world/tags/AIBros" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AIBros</span></a> love conflating the twos.</p>
Antonio Lieto<p>Happy birthday to Cognitive Design for Artificial Minds (<a href="https://lnkd.in/gZtzwDn3" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">lnkd.in/gZtzwDn3</span><span class="invisible"></span></a>) that was released 4 years ago!</p><p>Since then its ideas have been presented and discussed widely in the research fields of AI/Cognitive Science/Robotics and - nowadays - both the possibilities and the limitations of: <a href="https://fediscience.org/tags/LLMs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLMs</span></a>, <a href="https://fediscience.org/tags/GenerativeAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GenerativeAI</span></a> and <a href="https://fediscience.org/tags/ReinforcementLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ReinforcementLearning</span></a> (already envisioned and discussed in the book) have become a common topic of research interests in the AI community and beyond. <br>Similarly also the topic concerning the evaluation - in human-like and human-level terms - of the current AI systems has become a critical theme related to the problem Anthropomorphic interpretation of AI output (see e.g. <a href="https://lnkd.in/dVi9Qf_k" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">lnkd.in/dVi9Qf_k</span><span class="invisible"></span></a> ). <br>Book reviews have been published on ACM Computing Reviews (2021) <a href="https://lnkd.in/dWQpJdkV" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">lnkd.in/dWQpJdkV</span><span class="invisible"></span></a> and on Argumenta (2023): <a href="https://lnkd.in/derH3VKN" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">lnkd.in/derH3VKN</span><span class="invisible"></span></a></p><p>I have been invited to present the content of the book in over 20 official scientific events in international conferences, Ph.D Schools in US, China, Japan, Finland, Germany, Sweden, France, Brazil, Poland, Austria and, of course, Italy. </p><p>A news I am happy to share is that Routledge/Taylor &amp; Francis contacted me few weeks ago for a second edition! Stay tuned!</p><p>The <a href="https://fediscience.org/tags/book" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>book</span></a> is available in many webstores:<br>- Routledge: <a href="https://lnkd.in/dPrC26p" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">lnkd.in/dPrC26p</span><span class="invisible"></span></a><br>- Taylor &amp; Francis: <a href="https://lnkd.in/dprVF2w" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">lnkd.in/dprVF2w</span><span class="invisible"></span></a><br>- Amazon: <a href="https://lnkd.in/dC8rEzPi" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">lnkd.in/dC8rEzPi</span><span class="invisible"></span></a></p><p><span class="h-card" translate="no"><a href="https://a.gup.pe/u/academicchatter" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>academicchatter</span></a></span> <span class="h-card" translate="no"><a href="https://a.gup.pe/u/cognition" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>cognition</span></a></span> <br><a href="https://fediscience.org/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://fediscience.org/tags/minimalcognitivegrid" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>minimalcognitivegrid</span></a> <a href="https://fediscience.org/tags/CognitiveAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CognitiveAI</span></a> <a href="https://fediscience.org/tags/cognitivescience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cognitivescience</span></a> <a href="https://fediscience.org/tags/cognitivesystems" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cognitivesystems</span></a></p>
Python Weekly 🐍<p>Implemented 18 RL Algorithms in a Simpler Way</p><p><a href="https://github.com/FareedKhan-dev/all-rl-algorithms" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/FareedKhan-dev/all-</span><span class="invisible">rl-algorithms</span></a></p><p>Discussions: <a href="https://discu.eu/q/https://github.com/FareedKhan-dev/all-rl-algorithms" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">discu.eu/q/https://github.com/</span><span class="invisible">FareedKhan-dev/all-rl-algorithms</span></a></p><p><a href="https://mastodon.social/tags/programming" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>programming</span></a> <a href="https://mastodon.social/tags/python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>python</span></a> <a href="https://mastodon.social/tags/reinforcementlearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reinforcementlearning</span></a></p>
Dr. Anna Latour<p>My colleagues at TU Delft are seeking to hire a postdoc to work on Applied Planning and Scheduling under Uncertainty, with applications in modelling supply chain scenarios for offshore wind farm installation: <a href="https://careers.tudelft.nl/job/Delft-Postdoc-in-Applied-Planning-and-Scheduling-under-Uncertainty-2628-CD/814890902/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">careers.tudelft.nl/job/Delft-P</span><span class="invisible">ostdoc-in-Applied-Planning-and-Scheduling-under-Uncertainty-2628-CD/814890902/</span></a></p><p><a href="https://mathstodon.xyz/tags/AcademicMastodon" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AcademicMastodon</span></a> <a href="https://mathstodon.xyz/tags/PostdocLife" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PostdocLife</span></a> <a href="https://mathstodon.xyz/tags/Hiring" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Hiring</span></a> <a href="https://mathstodon.xyz/tags/Research" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Research</span></a> <a href="https://mathstodon.xyz/tags/Planning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Planning</span></a> <a href="https://mathstodon.xyz/tags/Scheduling" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Scheduling</span></a> <a href="https://mathstodon.xyz/tags/ReasoningUnderUncertainty" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ReasoningUnderUncertainty</span></a> <a href="https://mathstodon.xyz/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mathstodon.xyz/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ArtificialIntelligence</span></a> <a href="https://mathstodon.xyz/tags/JobSearch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>JobSearch</span></a> <a href="https://mathstodon.xyz/tags/Vacancy" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Vacancy</span></a> <a href="https://mathstodon.xyz/tags/AcademicChatter" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AcademicChatter</span></a> <a href="https://mathstodon.xyz/tags/Career" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Career</span></a> <a href="https://mathstodon.xyz/tags/CombinatorialOptimisation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CombinatorialOptimisation</span></a> <a href="https://mathstodon.xyz/tags/Sustainability" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Sustainability</span></a> <a href="https://mathstodon.xyz/tags/EnergyTransition" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EnergyTransition</span></a> <a href="https://mathstodon.xyz/tags/Wind" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Wind</span></a> <a href="https://mathstodon.xyz/tags/WindEnergy" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>WindEnergy</span></a> <a href="https://mathstodon.xyz/tags/ReinforcementLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ReinforcementLearning</span></a> <a href="https://mathstodon.xyz/tags/ML" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ML</span></a> <a href="https://mathstodon.xyz/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://mathstodon.xyz/tags/WindTurbines" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>WindTurbines</span></a> <a href="https://mathstodon.xyz/tags/ComputerScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ComputerScience</span></a> <a href="https://mathstodon.xyz/tags/Optimisation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Optimisation</span></a> <a href="https://mathstodon.xyz/tags/Optimization" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Optimization</span></a> <a href="https://mathstodon.xyz/tags/CombinatorialOptimization" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CombinatorialOptimization</span></a> <a href="https://mathstodon.xyz/tags/PostDoc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PostDoc</span></a> <a href="https://mathstodon.xyz/tags/AcademicCareer" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AcademicCareer</span></a> <a href="https://mathstodon.xyz/tags/Academia" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Academia</span></a> <a href="https://mathstodon.xyz/tags/AcademicJob" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AcademicJob</span></a> <a href="https://mathstodon.xyz/tags/AcademicJobs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AcademicJobs</span></a> <a href="https://mathstodon.xyz/tags/TUDelft" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TUDelft</span></a></p>
Sean Patrick<p>New instance, new <a href="https://wandering.shop/tags/introduction" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>introduction</span></a>! </p><p>I'm a <a href="https://wandering.shop/tags/DataScientist" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataScientist</span></a> with a background in <a href="https://wandering.shop/tags/ReinforcementLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ReinforcementLearning</span></a> and <a href="https://wandering.shop/tags/ElectricalEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ElectricalEngineering</span></a>. Well, that's what my resume says, but really I'm a <a href="https://wandering.shop/tags/poet" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>poet</span></a> and a SF/F <a href="https://wandering.shop/tags/writer" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>writer</span></a>. I love to play <a href="https://wandering.shop/tags/DnD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DnD</span></a> and other <a href="https://wandering.shop/tags/TTRPGs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TTRPGs</span></a>.</p><p>I use they/them pronouns, and "Dr." not "Mr.", please and thank you.</p><p>I maintain a blog at www.seanpatrick.phd which includes a current list of publications, including my debut sonnet collection, "Love, Death, and Other Surprises."</p>
Dr. Carlotta A. Berry, PhD<p><a href="https://blacktwitter.io/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://blacktwitter.io/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://blacktwitter.io/tags/BiasInAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BiasInAI</span></a> <a href="https://blacktwitter.io/tags/STEMSaturday" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>STEMSaturday</span></a> <a href="https://blacktwitter.io/tags/DeepLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeepLearning</span></a> <a href="https://blacktwitter.io/tags/ComputerVision" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ComputerVision</span></a> <a href="https://blacktwitter.io/tags/Robotics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Robotics</span></a> <a href="https://blacktwitter.io/tags/ReinforcementLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ReinforcementLearning</span></a> </p><p>Meet the editors of "Mitigating Bias in Machine Learning" Dr. Carlotta Berry and Dr. Brandeis Hill Marshall (Brandeis Marshall, PhD) <br>This practical guide shows, step by step, how to use machine learning to carry out actionable decisions that do not discriminate based on numerous human factors, including ethnicity and gender.<br>On Sale On Amazon <a href="https://a.co/d/dtMizVH" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="">a.co/d/dtMizVH</span><span class="invisible"></span></a></p>
Brandon Rohrer<p>Adding my love letter to</p><p>arxiv.org/pdf/2304.01315</p><p>Empirical Design in Reinforcement Learning<br>by<br>Andrew Patterson, Samuel Neumann, Martha White, Adam White</p><p>JMLR 25 (2024) 1-63</p><p><a href="https://recsys.social/tags/ReinforcementLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ReinforcementLearning</span></a></p><p>These aren’t the heroes we deserve, but they are the heroes we need.</p>
Brandon Rohrer<p>If you've ever worked with a physical robot and <a href="https://recsys.social/tags/ReinforcementLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ReinforcementLearning</span></a> you've had to deal with delays. Thinking takes time, even at computer speeds, and the world doesn't stop.</p><p>One way to minimize the delays is for the to world to act on new commands mid-cycle, rather than wait for its next turn.</p><p><a href="https://www.brandonrohrer.com/rl_noninteger_delay" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">brandonrohrer.com/rl_nonintege</span><span class="invisible">r_delay</span></a></p>
Python Weekly 🐍<p>[Project] PyMAB: An exploratory Python Library for Multi-Armed Bandits</p><p><a href="https://github.com/danielaLopes/pymab" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">github.com/danielaLopes/pymab</span><span class="invisible"></span></a></p><p>Discussions: <a href="https://discu.eu/q/https://github.com/danielaLopes/pymab" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">discu.eu/q/https://github.com/</span><span class="invisible">danielaLopes/pymab</span></a></p><p><a href="https://mastodon.social/tags/programming" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>programming</span></a> <a href="https://mastodon.social/tags/python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>python</span></a> <a href="https://mastodon.social/tags/reinforcementlearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reinforcementlearning</span></a></p>
Mattia Rigotti<p>📕 Dimitri Bertsekas just release a new edition of his <a href="https://mastodon.social/tags/ReinforcementLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ReinforcementLearning</span></a> book with added chapters on transformers and LLMs. Freely available here:<br><a href="http://web.mit.edu/dimitrib/www/RLbook.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">http://</span><span class="ellipsis">web.mit.edu/dimitrib/www/RLboo</span><span class="invisible">k.html</span></a></p><p><a href="https://mastodon.social/tags/RL" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RL</span></a> <a href="https://mastodon.social/tags/lecture" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>lecture</span></a> <a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a></p>
Python Weekly 🐍<p>What could be causing my Q-Loss values to diverge (SAC + Godot &lt;-&gt; Python)</p><p><a href="https://github.com/philipjball/SAC_PyTorch" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/philipjball/SAC_PyT</span><span class="invisible">orch</span></a></p><p>Discussions: <a href="https://discu.eu/q/https://github.com/philipjball/SAC_PyTorch" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">discu.eu/q/https://github.com/</span><span class="invisible">philipjball/SAC_PyTorch</span></a></p><p><a href="https://mastodon.social/tags/programming" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>programming</span></a> <a href="https://mastodon.social/tags/python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>python</span></a> <a href="https://mastodon.social/tags/reinforcementlearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reinforcementlearning</span></a></p>
Nick Byrd, Ph.D.<p>You may be familiar with the famous “Two Dogmas…” paper in Philosophical Review (1951).</p><p>Now there’s a “Three Dogmas of Reinforcement Learning” paper, with alternatives (RLC 2024)<br><a href="https://david-abel.github.io/tdorl.pdf" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">david-abel.github.io/tdorl.pdf</span><span class="invisible"></span></a></p><p>1. Focus on agents too (not just environment)<br>2. Learning may be better conceived of as adaption (rather than finding a solution)<br>3. Beware of explicating goals as reward maximization</p><p><a href="https://nerdculture.de/tags/CogSci" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CogSci</span></a> <a href="https://nerdculture.de/tags/ComputerScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ComputerScience</span></a> <a href="https://nerdculture.de/tags/stats" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>stats</span></a> <a href="https://nerdculture.de/tags/ReinforcementLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ReinforcementLearning</span></a> <a href="https://nerdculture.de/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://nerdculture.de/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://nerdculture.de/tags/PhilosophyOfScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PhilosophyOfScience</span></a> <a href="https://nerdculture.de/tags/Economics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Economics</span></a></p>
ITSPmagazine 🎙️✨:verified:<p>🎙️ ✨ A new episode has been published on <span class="h-card" translate="no"><a href="https://techhub.social/@ITSPmagazine" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>ITSPmagazine</span></a></span> </p><p>Show: On Location With <span class="h-card" translate="no"><a href="https://infosec.exchange/@Marcociappelli" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>Marcociappelli</span></a></span> and <span class="h-card" translate="no"><a href="https://infosec.exchange/@seanmartin" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>seanmartin</span></a></span> </p><p>Episode: Deep Backdoors in Deep Reinforcement Learning Agents | A Black Hat USA 2024 </p><p>Guests: Vas Mavroudis and Jamie Gawith</p><p>Podcast format: Video &amp; Audio</p><p><a href="https://techhub.social/tags/ReinforcementLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ReinforcementLearning</span></a> <a href="https://techhub.social/tags/BHUSA24" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BHUSA24</span></a> <a href="https://techhub.social/tags/cybersecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cybersecurity</span></a> <a href="https://techhub.social/tags/podcast" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>podcast</span></a></p><p>Enjoy!</p><p>📺 Watch the episode video on YouTube and subscribe to ITSPmagazine Channel here 👉 <a href="https://www.youtube.com/watch?v=pf3bdyzG1lA" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">youtube.com/watch?v=pf3bdyzG1l</span><span class="invisible">A</span></a></p><p>📻 If you prefer to listen to the audio podcast, enjoy it here<br>👇<br><a href="https://on-location-with-sean-martin-and-marco-ciappelli.simplecast.com/episodes/deep-backdoors-in-deep-reinforcement-learning-agents-a-black-hat-usa-2024-conversation-with-vas-mavroudis-and-jamie-gawith-on-location-coverage-with-sean-martin-and-marco-ciappelli" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">on-location-with-sean-martin-a</span><span class="invisible">nd-marco-ciappelli.simplecast.com/episodes/deep-backdoors-in-deep-reinforcement-learning-agents-a-black-hat-usa-2024-conversation-with-vas-mavroudis-and-jamie-gawith-on-location-coverage-with-sean-martin-and-marco-ciappelli</span></a></p><p>🖥️ More about our Black Hat USA 2024 coverage<br>👇<br><a href="https://www.itspmagazine.com/black-hat-usa-2024-hacker-summer-camp-2024-event-coverage-in-las-vegas" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">itspmagazine.com/black-hat-usa</span><span class="invisible">-2024-hacker-summer-camp-2024-event-coverage-in-las-vegas</span></a></p>
Carl Gold, PhD<p><span class="h-card" translate="no"><a href="https://mastodon.social/@seanpatrickphd" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>seanpatrickphd</span></a></span> it’s a small world (fediverse) I am going to the <a href="https://sigmoid.social/tags/RLC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RLC</span></a> <a href="https://sigmoid.social/tags/reinforcementlearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reinforcementlearning</span></a> conference. Anyone else?</p>
Sean Patrick<p>Anyone else on the Fediverse headed to <a href="https://mastodon.social/tags/AmherstMA" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AmherstMA</span></a> for <a href="https://mastodon.social/tags/RLC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RLC</span></a> in two weeks?</p><p><a href="https://mastodon.social/tags/ReinforcementLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ReinforcementLearning</span></a> <a href="https://mastodon.social/tags/academia" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>academia</span></a></p>
Carl Gold, PhD<p>Someone just shared this awesome comic with me. Does anyone know the original source? (I can't read the small signature.) 3 Complaining <a href="https://sigmoid.social/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machinelearning</span></a> robots 🤖 : <a href="https://sigmoid.social/tags/SupervisedLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SupervisedLearning</span></a> - they gave me so much to read, and test! <a href="https://sigmoid.social/tags/unsupervised" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>unsupervised</span></a> - Me too. But at least they told you the answers. <a href="https://sigmoid.social/tags/reinforcementlearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reinforcementlearning</span></a> - At least you don't get punished for every wrong action. 😆</p>