Provenance:Dataset:TEIAS v2025.1Model:PPO Lab fullRun:1 Dec 2025lab_ppo_20251201_091523Seeded

🔬

PPO fine-tune (LR 3e-4)

Tier B — Full✓ completed

lab_ppo_20251201_091523

Interpretation Guardrail

These results are scenario-based projections, not forecasts. They reflect model assumptions about technology costs, policy choices, and demand trajectories. Actual outcomes will differ. Always consult the full methodology and assumption registry before drawing policy conclusions.

↑Derived from:rl_ppo_20251127_114523parent_run_id

Frozen Metrics Snapshot

READ-ONLY · Not recomputed

Cost Reduction

−19.2%

Convergence Score

96/100

Policy Stability

94/100

Final Reward

-278.3

Training Loss

0.00290

Actual Runtime

34s

Configuration

Algorithm

PPO

Tier

B — Full

Learning Rate

0.0003

Total Steps

500,000

Seed

99

Created At

01/12/2025, 10:15:23

Est. Runtime

38s (cap: 300s)

Immutable

✓ Yes

Rate Limit & Cap at Run Time

Hourly usage: 1/5Daily usage: 3/20Concurrent: 0/3Queued: No

Run Lineage

🧪Experiment Run🔬Labs Full Run👁Labs Preview

🧪

rl_ppo_20251127_114523Experiment Rununknown

unknown

1 node in lineage. Lab runs are linked to their parent via parent_run_id. Original experiment runs are immutable — only lab runs can derive from them.

Derive a new run from this →← Run History

📎 Cite this — PPO fine-tune (LR 3e-4)

Önderol, S. (2025). Lab run: PPO fine-tune (LR 3e-4) [full sandbox]. renewabletransition.org/transition/labs/run/lab_ppo_20251201_091523