You can deploy this model and start earning money today!

hajirazin/
learnfinance-models-sac

Name: learnfinance-models-sac
Availability: InStock

sac

reinforcement-learning

portfolio-optimization

finance

patchtst-forecasts

learnfinance

Views

No views yet

LearnFinance SAC Model - v2026-09-04_05edd9bb

SAC v3 masked-attention portfolio allocator with ranked stock tokens.

Model Details

Version: v2026-09-04_05edd9bb
Model Type: SAC v3 (masked attention, 30 stock slots + CASH)
Training Window: 2016-01-01 to 2026-09-04
Symbols: 15 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
metadata.json - SAC v3 schema, architecture, slot map, and audit metadata
sac_v3_auxiliary.json - HMM parameters/scaler/labels, causal cutoff state, and market tail

Metrics

Actor Loss: 1.0995707511901855
Critic Loss: 0.3260440230369568
Avg Episode Return: 0.20918973136685962
Avg Episode Sharpe: 0.1370496263238117
Eval Sharpe: 1.3595824789700572
Eval CAGR: 0.3711349932559931
Eval Max Drawdown: 0.2254343596019483

Usage

python

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

storage = SACHuggingFaceModelStorage(
    repo_id="hajirazin/learnfinance-models-sac",
    local_cache=SACHalalFilteredModelStorage(),
)
artifacts = storage.download_model(version="v2026-09-04_05edd9bb")