ec257febe4
1. Backtest hold enforcement: hold_time tracked at portfolio[5], min_hold_bars override in backtest_env_step. Train/eval mismatch fixed. 2. Documented evaluator strategy: Layer 2 in env_step, not action masking. 3. Trial budget observer: shared Arc<AtomicUsize> counter — budget enforced. 4. CVaR threshold: 0.05/sqrt(bars_per_day) instead of hardcoded 0.003. 5. MIN_TRADES_DEGENERATE constant, dynamic test vector dimensions. 6. Integration pending — local hyperopt next. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
ml
10-model ML ensemble for the Foxhunt HFT system, built on Candle v0.9.1.
Models
- DQN (Rainbow) — deep Q-network with prioritized replay, dueling heads, noisy nets
- PPO — proximal policy optimization with GAE, LSTM policies, clip-higher
- TFT — temporal fusion transformer for multi-horizon forecasting
- Mamba2 — state space model for sequence prediction
- Liquid Networks — biologically inspired networks for non-stationary data
- TLOB — transformer-based limit order book analysis
- KAN — Kolmogorov-Arnold networks
- xLSTM — extended LSTM architecture
- TGGN — temporal graph neural network
- Diffusion — diffusion-based generative model
Key Modules
ensemble— model ensemble coordination and confidence aggregationhyperopt— PSO-based hyperparameter optimization with per-model adapterstrainers— unified training loops (DQN, PPO, supervised)inference—InferenceAdaptertrait for predictioncheckpoint— model checkpointing and restorationevaluation— walk-forward evaluation pipeline
Usage
use ml::dqn::DQN;
use ml::ppo::PpoTrainer;