Discussion of article "Applying Monte Carlo method in reinforcement learning" - page 2

 
mastil55:

Hi Maxim, thank u for your work, i was trying to test your code, however it shows me some errors in the mq4 file with the following text

'getRDFstructure' - function already defined and has different type RL_Monte_Carlo.mqh 76 11

'RecursiveElimination' - function already defined and has different type RL_Monte_Carlo.mqh 133 11

'updatePolicy' - function already defined and has different type RL_Monte_Carlo.mqh 221 11

'updateReward' - function already defined and has different type RL_Monte_Carlo.mqh 236 11

'setAgentSettings' - function already defined and has different type RL_Monte_Carlo.mqh 361 12

'updatePolicies' - function already defined and has different type RL_Monte_Carlo.mqh 373 12

'updateRewards' - function already defined and has different type RL_Monte_Carlo.mqh 380 12

Do you know how to solve that issue?

hi, you just need to add "void" before all functions, just new compiler of MT5

 

I am still trying to understand how to configure the inputs I am lay in the subject RL but it would be possible to apply this technique to the book of offers market depth as i done on NN sorry for newbie question!!! other thing is possible to use tensorflow model ! thanks in advance you are the best man!

 

Hi, I've been back-testing this code for hours. I wouldn't say it's learning much. The results seem pretty random with each pass and don't seem to progressively improve.

I would love to help out on this topic. I'm going to hack this code a bit and see what I can make it do. It's quite a learning curve for me at the moment but I find it intriguing.

 
chemmens:

Hi, I've been back-testing this code for hours. I wouldn't say it's learning much. The results seem pretty random with each pass and don't seem to progressively improve.

I would love to help out on this topic. I'm going to hack this code a bit and see what I can make it do. It's quite a learning curve for me at the moment but I find it intriguing.

I wish you good luck with hacking source code

 
Suporte Trading:

I am still trying to understand how to configure the inputs I am lay in the subject RL but it would be possible to apply this technique to the book of offers market depth as i done on NN sorry for newbie question!!! other thing is possible to use tensorflow model ! thanks in advance you are the best man!

You can apply it to everything you want, it's just example with row price returns, without any exogenous info or order book 

 
Most Impressive work as usual!, I have been enjoying it greatly. I was able to use it similarly with comparable results, thank you for sharing.
 
Brilliant, enjoying the articles and running the code. Thanks!!
 
This is the most amazing method I see long time, it have a lot of potential! You have a brilliant mind. Thank you for sharing!
 
'getRDFstructure' - unexpected token, probably type is missing? RL_Monte_Carlo.mqh                      76      12
'getRDFstructure' - function already defined and has different type     RL_Monte_Carlo.mqh              76      12
see declaration of 'CRLAgent::getRDFstructure'  RL_Monte_Carlo.mqh                                      43      22
'RecursiveElimination' - unexpected token, probably type is missing?    RL_Monte_Carlo.mqh              133     11
'RecursiveElimination' - function already defined and has different type        RL_Monte_Carlo.mqh      133     11
'updatePolicy' - unexpected token, probably type is missing?    RL_Monte_Carlo.mqh                      221     11
'updatePolicy' - function already defined and has different type        RL_Monte_Carlo.mqh              221     11



 
Hello I am obtaing many complex.mqh errors when try to compile monte_carlo_trader any guess ? Thanks. rogerio
Files:
cmpx_err.jpg  220 kb