jgrusewski 2f60e0cda0 fix(eval): train/eval parity - position tracking, cost differentiation, feature alignment ...

- Wire position-delta cost model: costs only apply on position changes,
  proportional to delta (not flat per-bar)
- Differentiate order types: Market=15bps, LimitMaker=5bps, IoC=10bps
- Apply urgency weight: Patient=0.5x, Normal=1.0x, Aggressive=1.5x
- Append 3 portfolio features (position, unrealized PnL, drawdown) to match
  training's 54-dim state vector (was 51, causing shape mismatch on load)
- Fix default num_actions 3->45 to match training's factored action space
- Add --bars-per-year CLI flag for per-symbol annualization
  (ES/NQ=347760, 6E=345000, ZN=105840)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-03 21:43:01 +01:00

..

baseline_common

fix(ml): wire spread_cost_bps into RL training — commission + spread = total tx cost

2026-03-01 22:10:43 +01:00

cuda_test.rs

chore: clean up examples, update ML binaries and risk tests

2026-02-27 01:33:18 +01:00

download_baseline.rs

chore: clean up examples, update ML binaries and risk tests

2026-02-27 01:33:18 +01:00

evaluate_baseline.rs

fix(eval): train/eval parity - position tracking, cost differentiation, feature alignment

2026-03-03 21:43:01 +01:00

evaluate_supervised.rs

fix(observability): dedicated OTLP runtime for sync training binaries

2026-03-02 18:54:10 +01:00

hyperopt_baseline_rl.rs

feat(hyperopt): make TPE the default optimizer

2026-03-03 18:50:02 +01:00

hyperopt_baseline_supervised.rs

feat(hyperopt): record elapsed_seconds metric in all hyperopt binaries

2026-03-03 00:10:02 +01:00

train_baseline_rl.rs

fix(dqn): atomic checkpoints, CUDA sync, NormStats hard error, q_value_std warning

2026-03-03 21:34:19 +01:00

train_baseline_supervised.rs

feat(supervised): record learning rate and epoch duration metrics

2026-03-03 00:10:00 +01:00