cfcaa68572
- DQNHyperparameters::conservative(): q_gap_threshold 0.0→0.05 (Tier 2 conviction gating active) - DQNHyperparameters::conservative(): her_ratio 0.0→0.2 (20% HER relabeling enabled) - All other Tier 2 defaults already active: count_bonus_coefficient=Some(0.1), curiosity_weight=0.1, use_cql=true, cql_alpha=0.1, enable_kelly_sizing=true, kelly_fractional=0.5, kelly_max_fraction=0.25 - Kelly sizing in experience_kernels.cu confirmed active: ps[14:17] wired, f*=(b*p-q)/b formula correct, half-Kelly safety applied, total_trades>=20 gate present Co-Authored-By: Claude Sonnet 4.6 <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;