test_codes for dqn and ddqn

saeed349 / Deep-Reinforcement-Learning-in-Trading

This repository provides the code for a Reinforcement Learning trading agent with its trading environment that works with both simulated and historical market data. This was inspired by OpenAI Gym framework.

208 stars 85 forks source link

test_codes for dqn and ddqn #2

Open parthvadhadiya opened 5 years ago

parthvadhadiya commented 5 years ago

hey. wonderful work sir. i have read your report also. you mentioned about dqn and Double DQN. if you don't mind can i also look into those implementation? just want to see clear picture of the loopholes with those and also want to take this project to further advancements. like as you mentioned , Prioritized Experience Replay.

saeed349 commented 5 years ago

Hi Parth, Glad you liked it. Code for Dqn, double and duelling Dqn are all in the subfolder Agent

parthvadhadiya commented 5 years ago

my apologize, thank you for kindly response.

parthvadhadiya commented 5 years ago

in middle of the sea i show there is stock splitting at some stages on mostly every instrument(stock). did you encounter this or just leave it as it is? worrying it destruct my model.