Files
foxhunt/example_backtest_results.json
jgrusewski 8ce7c52586 fix(dqn): Update evaluation script feature dimension from 125 to 128
- Fixed feature dimension mismatch in evaluate_dqn_main_orchestrator.rs
- Updated all 5 occurrences: state_dim, input comments, feature vector type
- Aligned with Wave 16D training (128 features: 125 market + 3 portfolio)

Issue: Validation backtest reveals 100% HOLD action collapse - requires reward
system investigation and redesign per latest RL research.
2025-11-08 18:28:56 +01:00

48 lines
1.3 KiB
JSON

{
"model_path": "/home/user/foxhunt/ml/trained_models/dqn_best_model.safetensors",
"data_path": "/home/user/foxhunt/test_data/ES_FUT_unseen.parquet",
"evaluation_timestamp": "2025-11-08T14:32:45.123456789Z",
"warmup_bars": 50,
"device": "cuda",
"total_runtime_sec": 2.453,
"action_distribution": {
"buy_count": 1234,
"sell_count": 987,
"hold_count": 3456,
"buy_pct": 21.5,
"sell_pct": 17.2,
"hold_pct": 61.3,
"total_bars": 5677
},
"avg_q_values": {
"buy_avg": 0.4523,
"sell_avg": -0.1234,
"hold_avg": 0.8912
},
"inference_performance": {
"mean_latency_us": 342.5,
"median_latency_us": 325,
"p50_latency_us": 325,
"p95_latency_us": 412,
"p99_latency_us": 487,
"min_latency_us": 198,
"max_latency_us": 1243
},
"policy_consistency": {
"total_switches": 1456,
"switch_rate": 0.2564,
"interpretation": "Moderate - Healthy adaptive behavior"
},
"production_readiness": {
"latency_p99_ok": true,
"latency_p99_threshold_us": 5000,
"latency_p99_actual_us": 487,
"consistency_ok": true,
"consistency_threshold_pct": "10-30%",
"consistency_actual_pct": 25.64,
"balanced_actions_ok": true,
"q_values_finite_ok": true,
"overall_ready": true
}
}