{
  "docId": "019dd923-5e88-73ef-bd5c-f341d4394195",
  "docSlug": "46f66c49fd159048",
  "documentTitle": "2018 Air Street Capital The State of AI Report 2018",
  "authorId": "AirStreetCapital",
  "authorName": "Air Street Capital",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "vc_research",
  "sourceTypeLabel": "VC research",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.777,
  "pageNumber": 36,
  "pageCount": 156,
  "prevPage": 35,
  "nextPage": 37,
  "slideType": "other",
  "function": "present_framework",
  "density": "balanced",
  "nDataPoints": 0,
  "notes": "The diagram shows the standard RL feedback loop: Agent receives observations and rewards, and performs actions.",
  "elementsJson": [
    "process_diagram",
    "photo"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5c-f341d4394195/36",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5c-f341d4394195",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5c-f341d4394195.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5c-f341d4394195#slide-36",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "A game is the world model used by a reinforcement learning (RL) system to learn behaviors by trial and error",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-41ac-7180-a811-a6b224712810",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.5,
        "w": 0.9,
        "x": 0.05,
        "y": 0.35
      },
      "kind": "diagram",
      "text": "Reinforcement Learning Loop",
      "attrs": null,
      "subkind": "process",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "1706b22d-db21-4d80-84e0-157dbcc5dc5d",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.95,
        "x": 0.02,
        "y": 0.22
      },
      "kind": "paragraph",
      "text": "A game is the world model used by a reinforcement learning (RL) system to learn behaviors by trial and error",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "af0a581e-be8a-465c-9568-904deefb4347",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.15,
        "x": 0.82,
        "y": 0.94
      },
      "kind": "paragraph",
      "text": "stateof.ai 2018",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "b849abd6-8eca-4154-8378-a29912fc0c62",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.95,
        "x": 0.02,
        "y": 0.15
      },
      "kind": "title",
      "text": "RL systems can learn goal-oriented behavior within simulated environments, i.e. games",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "7bc81f0f-0681-4090-80eb-9de12fc34737",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [],
  "frameworks": [
    {
      "name": "Reinforcement Learning Loop",
      "slug": null,
      "matchId": "c14f3493-0f12-432c-9d39-da62e5118bb9",
      "evidence": "Diagram showing Agent-Environment interaction via Observations, Rewards, and Actions",
      "confidence": 1
    }
  ],
  "arcBeats": [
    {
      "to": 69,
      "from": 4,
      "beatId": "019dd95a-0682-776c-8e34-ad4df4fe3ce7",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Definitions then research breakthroughs (transfer learning, hardware, RL) and talent supply data.",
      "position": 1,
      "confidence": 78,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 55,
      "from": 10,
      "beatId": "019dd95a-0682-776c-8e34-be65c7627fe7",
      "arcName": "The Onion",
      "arcSlug": "onion",
      "beatName": "First Layer",
      "beatSlug": "onion-first-layer",
      "evidence": "Hardware, vision, RL, bias - technical research layer.",
      "position": 2,
      "confidence": 55,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [
    {
      "to": 39,
      "from": 36,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3c-55bec48734a5",
      "evidence": "AlphaZero, OpenAI Dota2, world-model RL — three parallel evidence pieces of RL progress.",
      "position": 5,
      "objective": "Show RL agents now beat human experts across domains",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 78,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}