Enhancements

[Draichi]

Hello bro, After doing some changes I could make the bot beat the market by a small margin:

There is a lot of work to do but the main changes are:

• adding Ray so we can change the algorithms and the hyperparms
• Adding technical indicators to the csv
• changing the observable space (we do not need the past 5 days of data since with the indicators much more information is already been passed)
• changing the reward function

To train the agent in this images I used PPO with learning rate 5e-5 trained over 1.2 million timesteps with ourly data from 2019-04-19 16:00:00+00:00 to 2019-04-28 05:00:00+00:00 and then to evaluate I used data from 2019-04-28 06:00:00+00:00 to 2019-05-06 20:00:00+00:00.

You can see the whole code in this fork

Nice project mate, Thanks

[Usmaniatech]

I have cloned the repo. How do I run this so I can see these visualizations ? @Draichi

[Draichi]

@Usmaniatech you can clone this project and follow the instructions on the readme. If you face a problem you can open an issue, we are working in a new version of it

[searchlink]

@Draichi How to start your project Stock-Trading-Visualization?

[tyronehunt]

@Draichi - thanks for the updates to this! However when I clone the repo and run main.py the vizualisation has the bot never buying/selling - it just flat lines at 10,000. I also note that you have functions.py, vars.py, rollout.py and train.py which don't seem to be explicitly called anywhere in main.py / StockTradingEnv.py or StockTradingGraph.py. Any help would be much appreciated!?

[Draichi]

@tyronehunt @searchlink try this one https://github.com/Draichi/T-1000