c3ea0e57d1
Prevents memorization of fixed simulation parameters that exist only in training. Each epoch randomizes: - tx_cost_multiplier: U[0.5, 2.5] (was fixed 1.0) - spread: U[0.5x, 3.0x] base spread - fill_ioc_prob: U[0.65, 0.95] (was fixed 0.85) - fill_limit_min/max: randomized ranges - spread_cost: U[0.3, 0.8] fraction - Episode starts: ±25% stride jitter (was deterministic) - Episode length: ±25% base (was fixed) Controlled by enable_domain_randomization flag (default: true). 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;