jgrusewski 85b3f02af4 fix(hyperopt): enforce minimum 5 trials, skip hyperopt when trials=0 ...

The hyperopt binary was crashing with "trials (5) must be greater than
n_initial (5)" when --trials 0 was passed. Root cause: the bump logic
set trials = n_initial instead of max(5, n_initial + 1).

Fix: both hyperopt_baseline_rl and hyperopt_baseline_supervised now clamp
trials to max(5, n_initial + 1). Also add `when` condition to the
compile-and-train DAG so hyperopt step is skipped when trials=0, and
train-best gracefully handles missing hyperopt results.

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

2026-03-12 21:58:11 +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

fix(ml): remove dead parquet path, enable GPU features by default

2026-03-10 16:54:45 +01:00

evaluate_baseline.rs

fix(eval): use hyperopt max_position_absolute in walk-forward evaluator

2026-03-12 18:11:17 +01:00

evaluate_supervised.rs

fix(ml): remove dead parquet path, enable GPU features by default

2026-03-10 16:54:45 +01:00

hyperopt_baseline_rl.rs

fix(hyperopt): enforce minimum 5 trials, skip hyperopt when trials=0

2026-03-12 21:58:11 +01:00

hyperopt_baseline_supervised.rs

fix(hyperopt): enforce minimum 5 trials, skip hyperopt when trials=0

2026-03-12 21:58:11 +01:00

train_baseline_rl.rs

fix(ml): suppress unsafe-code warning on startup env::set_var calls

2026-03-12 08:46:17 +01:00

train_baseline_supervised.rs

feat(dqn): enable Branching DQN with 45 factored actions (5×3×3)

2026-03-11 22:00:13 +01:00