{
  "docId": "019dd923-5e88-73ef-bd5d-0856e1444fb9",
  "docSlug": "8757f1b44ef7f176",
  "documentTitle": "2024 Air Street Capital The State of AI Report 2024",
  "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": 69,
  "pageCount": 213,
  "prevPage": 68,
  "nextPage": 70,
  "slideType": "client_example",
  "function": "illustrate_case",
  "density": "balanced",
  "nDataPoints": 0,
  "notes": "The slide illustrates a technical process flow for automated RL task generation.",
  "elementsJson": [
    "headline_text",
    "paragraph",
    "flowchart"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-0856e1444fb9/69",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9#slide-69",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Imperial and UBC's OMNI-EPIC used LLMs to create a theoretically endless stream of RL tasks and environments to help agents build upon previously learned skills.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d15-08b6c50cebe4",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.48,
        "w": 0.68,
        "x": 0.16,
        "y": 0.45
      },
      "kind": "diagram",
      "text": "Process flow diagram of the OMNI-EPIC system including Task Archive, Task Generator, Environment Generator, Model of Interestingness, and Success Detector.",
      "attrs": null,
      "subkind": "process",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "319a22b3-38a8-4725-be95-a30d4d5eafd5",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.15,
        "w": 0.96,
        "x": 0.02,
        "y": 0.21
      },
      "kind": "paragraph",
      "text": "Imperial and UBC's OMNI-EPIC used LLMs to create a theoretically endless stream of RL tasks and environments to help agents build upon previously learned skills. The system generates executable Python code that can implement simulated environments and reward functions for each task, and employs a model to assess whether newly generated tasks are sufficiently novel and complex.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "3cbac20f-cc59-427e-8694-6190b41a11ed",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.65,
        "x": 0.02,
        "y": 0.14
      },
      "kind": "title",
      "text": "Could foundation models make it easier to train RL agents at scale?",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "64cf6e6f-c13c-457b-815a-e0cbd4ab99f5",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [],
  "frameworks": [
    {
      "name": "process",
      "slug": null,
      "matchId": "6ca2b1e2-a8b1-49d2-af2d-728d5803b54a",
      "evidence": "The slide depicts a cyclical workflow of task generation, environment creation, training, and evaluation.",
      "confidence": 0.8
    }
  ],
  "arcBeats": [
    {
      "to": 153,
      "from": 9,
      "beatId": "019dd95a-0682-776c-8e35-5f2398b8d1d0",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Exec summary + Research + Industry sections inventory the year",
      "position": 1,
      "confidence": 78,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 85,
      "from": 12,
      "beatId": "019dd95a-0682-776c-8e35-6d9d8ee06d0a",
      "arcName": "Voyage and Return",
      "arcSlug": "voyage-return",
      "beatName": "The Unknown",
      "beatSlug": "voyage-return-the-unknown",
      "evidence": "Research section explores frontier model uncharted territory",
      "position": 2,
      "confidence": 55,
      "parentBeatName": "Complication",
      "parentBeatSlug": "complication"
    }
  ],
  "loops": [
    {
      "to": 71,
      "from": 59,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3e-3f24b9b4c1e3",
      "evidence": "ARC challenge, planning failures, COT, open-endedness, MCTS, FunSearch, RL-LLM combos",
      "position": 8,
      "objective": "Catalogue progress and limits in reasoning research",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 76,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}