qlearning_v1-6 using PRB reward

Fixed render on q-learning_v1-3

PPO version

A2C trading results

Policy Gradient using Keras

Policy Gradiant using Keras

fin_rl_dqn_v1 notebook and first results

DQN_v1 converging

DQN cartpole v1

Qlearning in fin_rl_qlearning_v1.ipynb a few adjusts

Qlearning in fin_rl_qlearning_v1.ipynb missing gym package

Qlearning in fin_rl_qlearning_v1.ipynb missing gym package

Qlearning in fin_rl_qlearning_v1.ipynb

Using my own version of anytrading

Using my own version of anytrading

Update README.md

Update README.md

Upload fin_rl.png

Added Notebook trained using ETH with PPO

initial commit