qtrader
Q-Learning for Portfolio Management
Why Q-Learning?
- Learns the optimal action, rather than models the market.
- Adaptive to temporary changes of the market, due to its online training.
- Optimizes the long-term (cumulative) reward, rather than the instantaneous benefit.
Setup
macOS
source scripts/setup.sh
Resources
Textbooks
- Recurrent Neural Networks for Prediction: Learning Algorithms, Architectures and Stability by Danilo P. Mandic, Jonathon A. Chambers
- Analysis of Financial Time Series by Ruey S. Tsay
- Paul Wilmott on Quantitative Finance by Paul Wilmott
Papers
Reinforcement Learning & Trading
- Algorithm Trading using Q-Learning and Recurrent Reinforcement Learning
- Agent Inspired Trading Using Recurrent Reinforcement Learning and LSTM Neural Networks
- A Multi-agent Q-learning Framework for Optimizing Stock Trading Systems
- Deep Q-trading
- Reinforcement Learning in Online Stock Trading Systems
- Portfolio Management using Reinforcement Learning
- A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem