[{"data":1,"prerenderedAt":333},["ShallowReactive",2],{"project-31609217":3},{"id":4,"name":5,"line":5,"line_source":6,"title":7,"url":8,"domain":9,"maker":10,"posted_at":11,"year":12,"points":13,"comments":14,"rank_in_year":15,"shown_in_year":16,"top":17,"tier":18,"category":19,"subcategory":20,"format":21,"keywords":22,"reception":27,"sentiment":28,"stance_mix":29,"scored_comments":33,"aspects":34,"strip":41,"post_text":43,"what":44,"said":90,"maker_in_thread":189,"shape":197,"grid":199,"attempts":294,"same_week":295,"maker_shows":32,"maker_hidden":325,"reader_version":326,"card":327},"31609217","Fast Deep Reinforcement Learning Course","title","Show HN: Fast Deep Reinforcement Learning Course","https:\u002F\u002Fcourses.dibya.online\u002Fp\u002Ffastdeeprl","courses.dibya.online","gh1",1654268403,2022,148,37,406,2570,16,"notable","learning_science","online course","other",[23,24,25,26],"deep reinforcement learning","rllib","openai gym","reinforcement learning course","mixed",0.259,{"positive":30,"neutral":31,"mixed":32,"critical":32},6,3,2,13,{"performance":35,"execution":37,"idea":39,"design":40},{"positive":36,"critical":36},0,{"positive":36,"critical":38},1,{"positive":38,"critical":38},{"positive":31,"critical":36},[31,36,36,36,36,31,31,38,36,36,36,36,42,36,31,36,42,36,38,36,36,36,42,36,42,36,36,31,36,36,36,36,36,36,42,36,42],5,"I worked on this applied Deep Reinforcement Learning course for the better part of 2021. I made a Datacamp course [0] before, and this served as my inspiration to make an applied Deep RL series.\n\nNormally, Deep RL courses teach a lot of mathematically involved theory. You get the practical applications near the end (if at all).\n\nI have tried to turn that on its head. In the top-down approach, you learn practical skills first, then go deeper later. This is much more fun.\n\nThis course (the first in a planned multi-part series) shows how to use the Deep Reinforcement Learning framework RLlib to s",{"problem":45,"audience":51,"pricing":61,"motivation":62,"time_to_build":66,"stack":70,"openness":87,"stage":88,"team_size":89},{"value":46,"source":47,"evidence":48},"Learning deep RL starts with heavy math theory; this teaches practical skills first","maker",[49],{"id":50},"post",{"value":52,"source":53,"evidence":54},"Engineers and data scientists wanting practical deep RL skills","inferred",[55,58],{"id":56,"by":10,"text":57},"31610537","My experience matches yours. Recently, I was trying to solve an optimization problem using Deep RL. As usual, I had to run many experiments over several days using various tricks…",{"id":59,"by":10,"text":60},"31614468","Depends on what you mean by faster. Do you mean \"time to solution\" or \"time to inference\"? I think there are also more factors to take into consideration when considering the…",null,{"value":63,"source":47,"evidence":64},"Make deep RL more fun and practical by teaching applied skills first",[65],{"id":50},{"value":67,"source":47,"evidence":68},"Worked on it for the better part of 2021",[69],{"id":50},[71,75,79,83],{"value":72,"source":47,"evidence":73},"RLlib",[74],{"id":50},{"value":76,"source":47,"evidence":77},"OpenAI Gym",[78],{"id":50},{"value":80,"source":47,"evidence":81},"Teachable (LMS)",[82],{"id":50},{"value":84,"source":47,"evidence":85},"Latex Beamer",[86],{"id":50},"unknown","launched","solo",{"praise":91,"objections":112,"requests":140,"questions":145,"alternatives":160},[92,108],{"value":93,"source":94,"evidence":95},"Well-structured course with crisp presentation and good illustrations","commenter",[96,100,104],{"id":97,"by":98,"text":99},"31611181","robinson_k","Enrolled! Went through the detailed lesson plan and you have done a great job structuring the course. I am looking forward to doing it over the weekend. One suggestion: Instead…",{"id":101,"by":102,"text":103},"31609435","superfreek","Congrats on the launch. I have seen your Deep RL tutorials circulating on YouTube. I like your presentation style: crisp and precise.",{"id":105,"by":106,"text":107},"31610915","Fletch137","I love the illustrations in the slides. How long did it take you to learn flip chart drawing and how did you do the overlays in LaTeX?",{"value":109,"source":47,"evidence":110},"RLlib maker praised the course",[111],{"id":50},[113,120,130],{"value":114,"source":94,"evidence":115},"Courses teach API usage rather than fundamental theory",[116],{"id":117,"by":118,"text":119},"31615423","mywaifuismeta","This looks nicely done, but for anyone interested I'd like to mention that these courses aren't something that can replace learning the fundamental concepts and theories behind…",{"value":121,"source":94,"evidence":122},"RLlib is hard to modify for custom algorithms",[123,127],{"id":124,"by":125,"text":126},"31610388","cyber_kinetist","To be honest though, the practical side of things of RL can be a hit-and-miss in terms of \"fun\" depending on the person. It requires a lot of manual hand tuning, reward shaping,…",{"id":128,"by":125,"text":129},"31611729","Ah, good to meet here. I had experience using RLlib while participating in research back at grad school (which eventually became a SIGGRAPH conference paper this year!), and I've…",{"value":131,"source":94,"evidence":132},"Course pages blocked in Edge and strict tracking protection",[133,137],{"id":134,"by":135,"text":136},"31610111","thrill","When I visit the site using Edge, even with Adblockers disabled, I'm unable to view the courses listed as \"preview\", such as…",{"id":138,"by":10,"text":139},"31610209","I am sorry about that. Unfortunately, the same thing happens in Firefox when the tracking protection is set to \"strict\". This is apparently happening after Teachable updated…",[141],{"value":142,"source":94,"evidence":143},"Name notebooks uniquely so downloads do not overwrite",[144],{"id":97,"by":98,"text":99},[146,153],{"value":147,"source":94,"evidence":148},"Does the course use high-level Gym or lower-level code",[149],{"id":150,"by":151,"text":152},"31614015","pciexpgpu","Thank you for doing this! I haven't looked deeply enough, but does this course use a higher-level 'package' such as OpenAI Gym or teach at a lower-level? (Is lower-level stuff…",{"value":154,"source":94,"evidence":155},"Does the course cover transformers",[156],{"id":157,"by":158,"text":159},"31611772","mrfusion","Would this teach transformers? Or is that something else? Also any tips for finding a study group for learning the large language models? I can’t seem to self motivate.",[161,171,178,182],{"value":162,"source":94,"evidence":163},"Sutton and Barto book",[164,167],{"id":165,"by":118,"text":166},"31616791","IMO the best intro book is Sutton's [1], it's extremely accessible (little math background needed) and covers all basic concepts. Work through David Silver's course (search…",{"id":168,"by":169,"text":170},"31613878","axpy906","HF covers Decision Transfomers. Sutton and Barto is the best start for foundations. Start there.",{"value":172,"source":94,"evidence":173},"David Silver RL course",[174],{"id":175,"by":176,"text":177},"31611989","Asafp","Before jumping into Deep Reinforcement Learning I highly recommend doing the Reinforcement Learning course by David Silver [1]. [1]…",{"value":179,"source":94,"evidence":180},"Stable Baselines 3",[181],{"id":124,"by":125,"text":126},{"value":183,"source":94,"evidence":184},"Hugging Face deep RL class",[185],{"id":186,"by":187,"text":188},"31611576","abidlabs","May also be of interest: https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fdeep-rl-class",{"comments":190,"answered":30,"key":191},9,[192,193,194],{"id":56,"text":57},{"id":59,"text":60},{"id":195,"text":196},"31618075","I think the idea is not to replace learning the theory or math, but rather to just postpone it. Learning the practical aspects of an engineering discipline can provide the…",{"commenters":198,"max_depth":42,"maker_replies":190,"first_comment_mins":31,"lifespan_hours":198},22,[200,202,204,207,208,211,215,217,219,223,224,227,229,231,234,236,239,242,243,246,248,251,254,255,258,260,264,267,268,271,275,277,279,280,282,286,289],[124,36,31,201,125,36],"project\u002Fmixed\u002Fperformance",[56,36,36,203,10,38],"commenter\u002Fneutral\u002Fnone",[205,36,36,203,206,36],"31614046","InefficientRed",[59,36,36,203,10,38],[209,36,36,210,206,36],"31614848","other\u002Fneutral\u002Fnone",[212,36,31,213,214,36],"31610794","project\u002Fneutral\u002Fexecution","avna98",[128,36,31,216,125,36],"project\u002Fmixed\u002Fexecution",[117,38,38,218,118,36],"project\u002Fcritical\u002Fidea",[220,38,36,221,222,36],"31616722","other\u002Fneutral\u002Fdocs","sul_tasto",[165,38,36,221,118,36],[225,38,36,226,222,36],"31618890","commenter\u002Fpositive\u002Fdocs",[195,38,36,228,10,38],"project\u002Fpositive\u002Fidea",[97,32,42,230,98,36],"project\u002Fpositive\u002Fdesign",[232,32,36,233,10,38],"31611536","maker\u002Fpositive\u002Fdesign",[150,32,31,235,151,36],"project\u002Fneutral\u002Fnone",[237,32,36,238,10,38],"31614208","project\u002Fneutral\u002Fidea",[240,32,42,241,151,36],"31614231","maker\u002Fpositive\u002Fnone",[186,31,36,221,187,36],[134,244,38,245,135,36],4,"project\u002Fcritical\u002Fexecution",[138,244,36,247,10,38],"maker\u002Fneutral\u002Fexecution",[249,42,36,210,250,36],"31617162","khalilravanna",[252,42,36,210,253,36],"31617892","leaflets2",[105,30,42,233,106,36],[256,30,36,257,10,38],"31611164","maker\u002Fneutral\u002Fdesign",[101,259,42,233,102,36],7,[261,262,36,221,263,36],"31610332",8,"Buttons840",[265,262,36,221,266,36],"31619571","d4rkp4ttern",[157,190,31,238,158,36],[269,190,36,270,10,38],"31612113","commenter\u002Fneutral\u002Fidea",[272,190,36,273,274,36],"31612493","commenter\u002Fcritical\u002Fidea","rg111",[175,276,36,221,176,36],10,[278,276,36,221,274,36],"31612458",[168,276,36,221,169,36],[281,276,36,221,151,36],"31614042",[283,284,42,228,285,36],"31609278",11,"Baopab",[287,284,36,288,10,38],"31609343","project\u002Fneutral\u002Fperformance",[290,291,42,292,293,36],"31612436",12,"project\u002Fpositive\u002Fnone","sydthrowaway",[],[296,301,306,311,316,321],{"id":297,"name":298,"points":299,"category":300},"31607318","webOS Archive",439,"infrastructure",{"id":302,"name":303,"points":304,"category":305},"31595822","Svelvet",354,"dev_tools",{"id":307,"name":308,"points":309,"category":310},"31653726","The Bitcoin Note",344,"finance_crypto",{"id":312,"name":313,"points":314,"category":315},"31668814","Spiral Wiki",331,"security_privacy",{"id":317,"name":318,"points":319,"category":320},"31593726","quaxio.com",281,"games",{"id":322,"name":323,"points":324,"category":300},"31657527","Umbrel",225,false,"v2",{"id":328,"name":5,"line":5,"ai":325,"cat":19,"year":12,"points":13,"comments":14,"rec":27,"s":329,"top":17,"kw":330,"maker":10,"domain":9,"tier":18,"attempts":36,"strip":331,"url":8,"mix":332,"praise":93,"objection":114,"sub":20},31609217,0.26,[23,24,25,26],"3000033100005030501000505003000000505",[30,31,32,32],1793991046685]