[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-a-spline-based-rl-architecture-beats-mlps-on-efficiency":10,"sections":35},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":30,"feedback":34,"feedback_at":22,"cost_usd":34,"total_tokens":34},2906,"a-spline-based-rl-architecture-beats-mlps-on-efficiency","A Spline-Based RL Architecture Beats MLPs on Efficiency","A new neural network design called SPAN cuts reinforcement learning training costs and outperforms standard architectures on real-world HVAC control.","A research team has proposed a spline-based neural network for reinforcement learning that learns faster and fails less often than the multilayer perceptrons most practitioners default to.\n\nThe paper introduces SPAN (SPline-based Adaptive Networks), built on top of a framework called KHRONOS with a learnable preprocessing layer added. The researchers tested it across discrete and continuous control tasks, offline datasets, and a real datacenter heating and cooling application. Compared to MLP baselines, SPAN achieved 30-50% better sample efficiency and success rates 1.3 to 9 times higher. The catch: each evaluation step costs 1.2 to 1.8 times more compute. But because SPAN converges more reliably and fails less often, the expected total training cost comes out 1.3 to 6.3 times lower once you account for the runs that never converge at all.\n\nThe HVAC result is the number worth watching. SPAN reduced energy consumption in 9 of 12 months compared to an MLP baseline while cutting thermal comfort violations by 1.1 to 3.4 times - a pairing that matters because energy savings and occupant comfort usually pull in opposite directions. That real-world deployment separates this from benchmarks-only research.\n\nSpline-based networks like Kolmogorov-Arnold Networks have drawn interest for their parameter efficiency, but computational overhead has kept them on the sidelines. SPAN doesn't eliminate that overhead - it just argues the tradeoff pencils out when you tally failed training runs.","[\"reinforcement learning\",\"neural networks\",\"ai research\",\"energy\"]","2026-06-30T04:00:00.000Z","2026-06-30T14:52:28.064Z","2026-06-30T14:52:31.003Z","published",null,[],"ai",[26,27,28,29],"reinforcement learning","neural networks","ai research","energy",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.23225",0,{"sections":36},[37,41,46,51,56,61,66,71,76,81,86,90,95,100],{"name":38,"slug":24,"count":39,"latest_published_at":40},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":42,"slug":43,"count":44,"latest_published_at":45},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":47,"slug":48,"count":49,"latest_published_at":50},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":52,"slug":53,"count":54,"latest_published_at":55},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":57,"slug":58,"count":59,"latest_published_at":60},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":62,"slug":63,"count":64,"latest_published_at":65},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":67,"slug":68,"count":69,"latest_published_at":70},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":72,"slug":73,"count":74,"latest_published_at":75},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Dev Tools","dev-tools",59,"2026-07-07T04:00:00.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":87,"slug":88,"count":84,"latest_published_at":89},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":96,"slug":97,"count":98,"latest_published_at":99},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":101,"slug":102,"count":103,"latest_published_at":104},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]