{
  "apiVersion": "v1",
  "methodology": "https://sourcescore.org/methodology/",
  "canonical": "https://sourcescore.org/claims/00f224e1ccc158ef/",
  "claim": {
    "vertical": "ai-ml",
    "subject": "Proximal Policy Optimization (PPO)",
    "predicate": "introduced_in_paper",
    "object": "Proximal Policy Optimization Algorithms (Schulman et al., 2017)",
    "confidence": 1,
    "sources": [
      {
        "url": "https://arxiv.org/abs/1707.06347",
        "title": "Proximal Policy Optimization Algorithms",
        "publisher": "arXiv (Schulman, Wolski, Dhariwal, Radford, Klimov)",
        "publishedDate": "2017-07-20",
        "accessedDate": "2026-05-16",
        "type": "preprint",
        "excerpt": "We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a \"surrogate\" objective function using stochastic gradient ascent."
      },
      {
        "url": "https://openai.com/research/openai-baselines-ppo",
        "title": "Proximal Policy Optimization",
        "publisher": "OpenAI",
        "publishedDate": "2017-07-20",
        "accessedDate": "2026-05-16",
        "type": "official-blog"
      }
    ],
    "publishedAt": "2026-05-16T00:00:00Z",
    "lastVerified": "2026-05-16",
    "methodologyVersion": "veritas-v0.1",
    "tags": [
      "ppo",
      "reinforcement-learning",
      "foundational",
      "schulman",
      "2017",
      "openai",
      "rlhf"
    ],
    "id": "00f224e1ccc158ef",
    "statement": "Proximal Policy Optimization (PPO) introduced in paper: Proximal Policy Optimization Algorithms (Schulman et al., 2017)."
  },
  "signature": {
    "algorithm": "HMAC-SHA256",
    "signedBy": "did:web:sourcescore.org",
    "signedAt": "2026-05-16T00:00:00.000Z",
    "signature": "e9496ccad15298078027084850069195bde1bcb47a249278a1b193354b8cc9cd"
  },
  "citedAs": "Proximal Policy Optimization (PPO) introduced in paper: Proximal Policy Optimization Algorithms (Schulman et al., 2017). — SourceScore Claim 00f224e1ccc158ef (verified 2026-05-16, signed e9496cca…). https://sourcescore.org/claims/00f224e1ccc158ef/"
}