341a2cadf0
Adds curiosity-driven exploration (ForwardDynamicsModel + ICM reward), configurable branching DQN fields (num_order_types, num_urgency_levels), regime-conditional importance sampling with ADX/CUSUM thresholds, and GPU curiosity training kernel support. Also fixes remaining 5 clippy errors from WIP merge: - gpu_smoketest: add 8 missing DQNConfig fields - curiosity.rs: replace needless_range_loop with slice fill - benchmark files: remove redundant #[cfg_attr] on unconditionally ignored tests 40 files changed, +1486/-1068 lines. 0 clippy errors, 0 warnings. Co-Authored-By: Claude Opus 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;