hajirazin/learnfinance-models-sac-it-heavy

LearnFinance SAC Model - v2026-07-24_8abf2012

Soft Actor-Critic (SAC) portfolio allocation agent using dual forecasts (LSTM + PatchTST) as features.

Model Details

• Version: v2026-07-24_8abf2012
• Model Type: SAC (Soft Actor-Critic) with dual forecasts
• Training Window: 2016-01-01 to 2026-07-24
• Symbols: 12 stocks

Components

• actor.pt - Gaussian policy network
• critic.pt - Twin Q-value networks
• critic_target.pt - Target Q-value networks
• log_alpha.pt - Entropy temperature coefficient
• scaler.pkl - PortfolioScaler for state normalization
• symbol_order.json - Ordered list of portfolio symbols

Metrics

• Actor Loss: 0.6947705700111084
• Critic Loss: 0.0
• Avg Episode Return: 0.4465193736534414
• Avg Episode Sharpe: 0.25876177914003295
• Eval Sharpe: 1.9813125546474277
• Eval CAGR: 0.5397566636487405
• Eval Max Drawdown: 0.20373631577079032

Usage

from brain_api.storage.sac import SACHuggingFaceModelStorage
from brain_api.storage.sac.local import SACHalalFilteredModelStorage

storage = SACHuggingFaceModelStorage(
    repo_id="hajirazin/learnfinance-models-sac-it-heavy",
    local_cache=SACHalalFilteredModelStorage(),
)
artifacts = storage.download_model(version="v2026-07-24_8abf2012")