Ceruleanacg/Personae

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1407 stars · 342 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Personae is a Python library implementing deep reinforcement learning (DDPG, Double DQN, Dueling DQN, Policy Gradient) and supervised learning (DA-RNN, TreNet, LSTM) algorithms with TensorFlow for quantitative trading research. It includes a simulated financial market environment supporting stocks and futures that serves as a gym-style environment for training and evaluating these models.

Use cases

• apply deep reinforcement learning to stock trading
• predict stock prices with LSTM or attention RNN models
• simulate a financial market environment for trading agents
• reproduce RL trading papers like DDPG and Double DQN
• experiment with supervised learning for time series prediction in finance
• backtest trading strategies with neural network models

When to choose

• you want reference TensorFlow implementations of RL algorithms applied to trading
• you need a simple simulated market environment for stock or futures experiments
• you are doing research or coursework on deep RL for quantitative finance
• you want paper-faithful implementations of DA-RNN, TreNet, or DQN variants

When to avoid

• you need production-ready trading infrastructure or live broker integration
• you require high-frequency or intraday data - only day frequency is supported
• you want well-maintained software - the repo was under reconstruction and development has stalled
• you need sophisticated feature engineering - the included features are explicitly naive

Facets

library · maturity maintenance

reinforcement-learning machine-learning trading simulation reinforcement-learning machine-learning fintech time-series python quantitative-trading tensorflow stock-prediction gym-environment ddpg dqn lstm time-series-prediction docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Ceruleanacg/Personae")