{"type":"link","version":"1.0","title":"Confining self-improvement to in-distribution actions buys order-of-magnitude sample efficiency at the cost of exploration","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/in-distribution-constraint-trades-exploration-for-sample-efficiency","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}