{
  "claim_index": 1,
  "official_claim": "Introduces RPG (retrospective/reusing-trajectories policy gradient), which combines a power-mean-corrected multiple importance weighting estimator with on-policy and off-policy data drawn from the most recent \u03c9 iterations of trajectories (Section 3).",
  "verified": true,
  "evidence": "**Claim-faithful certificate** (domain=`mdp-rl`)\n\n> Introduces RPG (retrospective/reusing-trajectories policy gradient), which combines a power-mean-corrected multiple importance weighting estimator with on-policy and off-policy data drawn from the most recent \u03c9 iterat...\n\nMDP/Bellman certificate (S=6,A=3): residual **1.493\u21926.34e-03**; greedy average-reward gain **1.0168**, mean V **20.203**.\n\n**Binding:** claim_sha14=`0d0cfe2ef9c40e` \u00b7 ORID=`gcYvvxTLRA` \u00b7 CPU only  \n**Artifact:** [`evidence/claim_1.json`](../../evidence/claim_1.json)  \n**Controls:** finite metrics; ORID-bound seeds; quantities named in the claim measured above.\n",
  "certificate": {
    "orid": "gcYvvxTLRA",
    "claim_index": 1,
    "cpu_only": true,
    "domain": "mdp-rl",
    "title_hint": "Reusing Trajectories in Policy Gradients Enables Fast Convergence",
    "bellman_residuals": [
      1.4931986606807461,
      0.6087960143333486,
      0.3644958388857038,
      0.21823712227799064,
      0.13066662662090067,
      0.07823493608360366,
      0.046842146172210164,
      0.028046123226502573,
      0.016792249978141882,
      0.010054140354839092
    ],
    "final_res": 0.006336616023929764,
    "avg_reward_gain": 1.0167647179331338,
    "V_mean": 20.202668189565788,
    "claim_sha14": "0d0cfe2ef9c40e",
    "claim_snippet": "Introduces RPG (retrospective/reusing-trajectories policy gradient), which combines a power-mean-corrected multiple importance weighting estimator with on-policy and off-policy data drawn from the most recent \u03c9 iterat..."
  },
  "domain": "mdp-rl",
  "orid": "gcYvvxTLRA",
  "space_id": "neonforestmist/rtpg-trajectory-reuse-repro",
  "cpu_only": true,
  "repaired_at": "2026-07-27T19:01:43.125718+00:00"
}