eabc7ae36b
Three-phase hyperopt pipeline: Phase 1 (fast): fix architecture + reward, search dynamics (~17D) Phase 2 (full): fix dynamics, search architecture (~5D) Phase 3 (reward): fix dynamics + architecture, search reward weights (7D) Phase 3 is the fastest (~10s/trial) since only experience collection changes. CLI: --phase reward --hyperopt-params phase2_results.json Argo template runs all 3 phases sequentially. Phase 2 writes to _phase2_results.json, Phase 3 writes final _hyperopt_results.json. 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;