jgrusewski 118ceca4d5 fix(ml): update evaluate_baseline for 45 factored actions ...

Both DQN and PPO eval paths used old 3-action index matching (0=Buy,
1=Sell, 2=Hold). Now uses FactoredAction.target_exposure() for
exposure-weighted returns and order-type-specific transaction costs.
PPO path had .to_int() which doesn't exist on FactoredAction.

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

2026-03-02 15:41:24 +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(ml): update evaluate_baseline for 45 factored actions

2026-03-02 15:41:24 +01:00

evaluate_supervised.rs

feat(ml): wire Prometheus eval metrics into evaluate_supervised

2026-03-01 23:03:13 +01:00

hyperopt_baseline_rl.rs

feat(ml): add OTLP tracing to all 6 training/eval binaries

2026-03-01 23:03:13 +01:00

hyperopt_baseline_supervised.rs

feat(ml): add OTLP tracing to all 6 training/eval binaries

2026-03-01 23:03:13 +01:00

train_baseline_rl.rs

feat(ml): GPU saturation final — DQN PER deferral, PPO trajectory batching, Liquid/TGGN sync reduction, DoubleBuffer wiring

2026-03-02 15:41:23 +01:00

train_baseline_supervised.rs

feat(ml): add OTLP tracing to all 6 training/eval binaries

2026-03-01 23:03:13 +01:00