search

AI4Finance-Foundation / FinRL

FinRL: Financial Reinforcement Learning. 🔥
https://ai4finance.org
MIT License
10.11k stars 2.44k forks source link

result of trade #5

Closed pwner4810 closed 3 years ago

pwner4810 commented 3 years ago

hey sir thanks for your helpful article I've read your article in two form ensemble strategy and this model with comparison of backtesting result could you please speak about why this model is working better than ensemble strategy and what improvement are you going to implement in the new version of this model

BruceYanghy commented 3 years ago

hey sir thanks for your helpful article I've read your article in two form ensemble strategy and this model with comparison of backtesting result could you please speak about why this model is working better than ensemble strategy and what improvement are you going to implement in the new version of this model

I have been improving the state-of-the-art (SOTA) performance of the DRL algorithms in stock trading. I wouldn't say that that this model is better than the ensemble strategy. I will incorporate the ensemble strategy into the FinRL library in our next version.

pwner4810 commented 3 years ago

oh that's the point ! . thanks a lot just another you have skipped validation process is that a part of improving ? im definitely one of your fan because of you explanation documentation and of course knowledge thanks .

BruceYanghy commented 3 years ago

oh that's the point ! . thanks a lot just another you have skipped validation process is that a part of improving ? im definitely one of your fan because of you explanation documentation and of course knowledge thanks .

The validation process is just for model selection in ensemble strategy. In real life trading, it's better to have a paper trading stage to test the algorithm.

YangletLiu commented 3 years ago

Is this issue fixed, and can be closed?