{"type":"link","version":"1.0","title":"Casting multi-step reasoning as a Markov decision process makes an explicit world state, not just the next token, the thing being predicted","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/reasoning-as-mdp-state-action-reward","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}