{"type":"link","version":"1.0","title":"Every next-state observation is a free training signal an agent system already collects","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/next-state-signals-replace-explicit-reward-labels","thumbnail_url":"https://ai-arch.pages.dev/og/next-state-signals-replace-explicit-reward-labels.png","thumbnail_width":1200,"thumbnail_height":630}