36d076b344
- IQL mandatory: Option<GpuIqlTrainer> → GpuIqlTrainer (high + low tau) - Full pipeline in submit_aux_ops: populate_q_out → gather → train both → advantages → adv_sigma → per_sample_support → branch_scales → gap → epsilon - Delete v_range wrappers from FusedTrainingCtx - Delete adapt_v_range calls from training_loop.rs - Rename v_range_ptr → per_sample_support_ptr in experience collector - Fixed eval v_range in metrics.rs (wide fixed range for argmax) 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;