Skip to content
RT
Skip to main content
Provenance:Dataset:TEIAS v2025.1Model:DQN v1.0-disc5Run:27 Nov 2025rl_dqn_discrete_5lvl_202…Seeded

DQN v1.0-disc5 — Run Detail

Seeded Stochastic

Random seed fixed; reproducible on same hardware. Seed: 42. DQN with 5-level action discretisation. Documents precision loss from continuous→discrete projection.

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.

Frozen Metrics Snapshot

READ-ONLY · Not recomputed
Cost Reduction
−97.69%
Convergence Score
4913 / 100
Policy Stability
76 / 100
Final Episode Reward
4913.5
Final Training Loss
0.0098
Training Steps
2,600

These values are stored in frozen_metrics_snapshot and written at import time. They are never recalculated from raw artifacts.

Run Metadata

Run ID
rl_dqn_discrete_5lvl_20251127
Group ID
validation_runs
Source File
dqn_discrete5lvl_snapshot.json
Content Hash
d44e55f667788990…
Config Hash
cfghash_dqn_disc5_01
Created At
27/11/2025, 19:30:00 UTC
Immutable
✓ Yes (DB enforced)
Dataset Version
TEIAS v2025.1

Artifact Manifest (1)

frozen_artifact_manifest · Integrity verified
⚙️
5-level discrete action config
artifacts/dqn_disc5_20251127/config.json
configapplication/json3 KBsha256: dd44ee55ff66

Same Group: Validation & Stress Tests

rl_ppo_instability_test_01PPOCost ↓84.5%View →
rl_a3c_highre_20251103A3CCost ↓91.2%View →
forecast_lstm_v2_validation_20250815LSTMCost ↓0%View →

Traceability Chain

📦 Dataset: TEIAS v2025.1→🧪 Run: rl_dqn_discrete_5lvl_20251127→📊 1 Artifacts→📰 Insights

📎 Cite this page

Önderol, S. (2025). Experiment Run: DQN v1.0-disc5 — rl_dqn_discrete_5lvl_20251127. Retrieved from https://renewabletransition.org/transition/experiments/rl_dqn_discrete_5lvl_20251127
DQN — rl_dqn_discrete_5lvl_20251127 — Experiment | Renewable Transition