bfc3ffa9dc
Smoke train-fp7xx printed all 16 Phase-6/7/8 checkpoints clean through PER_PRIORITY_DONE. CAPTURE_DONE missing, exit changed 139→143 (SIGTERM) — capture_training_graph hangs or takes ~40s past PER_PRIORITY_DONE before Argo terminates the pod. Adds 14 CAPTURE_PHASE_* checkpoints across the 12 child captures + parent compose: BEGIN / PER_SAMPLE / COUNTERS / SPECTRAL / FORWARD / DDQN / AUX POST_AUX / ADAM_GRAD / ADAM_UPDATE / MAINTENANCE / IQL_MODULATE PER_PRIORITY / CHILDREN_STORED / PARENT_COMPOSED Diagnostic-only. Co-Authored-By: Claude Opus 4.7 (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;