[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-new-rl-method-keeps-competitive-robots-from-being-gamed":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},7554,"new-rl-method-keeps-competitive-robots-from-being-gamed","New RL Method Keeps Competitive Robots From Being Gamed","A two-stage training method keeps competitive robots effective without letting rivals exploit their safety rules.","A new robot-training method separates safety rules from the strategy that tries to win, and the split makes both harder to break.\n\nResearchers built a two-stage reinforcement learning framework called Safety to Competence (S2C) for robots in competitive tasks, tested in simulated tag-style \"touchdown games.\" Instead of training one policy to be safe and effective at the same time, the usual approach, S2C first trains a robust safety filter using adversarial RL, then embeds that filter into the environment while a separate policy learns to compete. The same filter stays active at deployment rather than being swapped out. The team frames the matchup as a safety-critical Markov game and shows mathematically that this filtering keeps a policy non-exploitable, provided opponents also commit to safe moves.\n\nIn simulation, S2C beat eight existing safe-RL baselines on win rate and Elo rating, and it also scored lowest on exploitability, meaning fewer openings a smart opponent could use against it. Hardware tests against a human opponent held up too. That matters because safety and competitiveness usually trade off against each other in robotics work; getting both to improve together is the harder result to fake.\n\nTouchdown games are a controlled testbed, not a factory floor or a battlefield, so whether this filter survives faster, less cooperative real-world opponents is still an open question.","[\"robotics\",\"reinforcement-learning\",\"ai-safety\",\"arxiv\"]","2026-09-24T04:00:00.000Z","2026-09-24T06:18:55.600Z","2026-09-24T06:19:00.823Z","published",null,[],"ai",[26,27,28,29],"robotics","reinforcement-learning","ai-safety","arxiv",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.27312",0,{"sections":36},[37,40,44,49,54,59,64,69,74,79,84,89,94,99],{"name":38,"slug":24,"count":39,"latest_published_at":18},"AI",4424,{"name":41,"slug":42,"count":43,"latest_published_at":18},"Security","security",724,{"name":45,"slug":46,"count":47,"latest_published_at":48},"Policy","policy",380,"2026-09-23T22:53:43.000Z",{"name":50,"slug":51,"count":52,"latest_published_at":53},"Deals","deals",221,"2026-09-24T08:00:00.000Z",{"name":55,"slug":56,"count":57,"latest_published_at":58},"Hardware","hardware",173,"2026-09-23T23:42:10.000Z",{"name":60,"slug":61,"count":62,"latest_published_at":63},"Science","science",136,"2026-09-24T09:00:00.000Z",{"name":65,"slug":66,"count":67,"latest_published_at":68},"Consumer Tech","consumer-tech",116,"2026-09-24T00:51:49.000Z",{"name":70,"slug":71,"count":72,"latest_published_at":73},"Software","software",85,"2026-09-23T20:00:00.000Z",{"name":75,"slug":76,"count":77,"latest_published_at":78},"Dev Tools","dev-tools",79,"2026-09-22T22:21:13.000Z",{"name":80,"slug":81,"count":82,"latest_published_at":83},"Startups","startups",66,"2026-09-23T17:28:38.000Z",{"name":85,"slug":86,"count":87,"latest_published_at":88},"Gaming","gaming",45,"2026-09-22T15:35:06.000Z",{"name":90,"slug":91,"count":92,"latest_published_at":93},"General","general",43,"2026-09-21T23:48:56.000Z",{"name":95,"slug":96,"count":97,"latest_published_at":98},"Reviews","reviews",27,"2026-09-22T13:00:00.000Z",{"name":100,"slug":101,"count":102,"latest_published_at":103},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]