rl_write_control_parameters function

Function to find and write the best control parameters.

This function is supposed to run on a weekly basis. Purpose of this function is to perform RL and trading simulation and find out the best possible control parameters for the RL function.

rl_write_control_parameters(
  x,
  path_control_files,
  num_trades_to_consider = 100
)

Arguments

• x: * dataset containing the trading results for one trading robot
• path_control_files: * path where control parameters will be saved
• num_trades_to_consider: * number of last trades to use for RL modeling simulations, default value 100

Returns

Function writes best control parameters to be used by the Reinforcement Learning Function

Details

Function is used by the R script Adapt_RL_control.R

Examples

dir <- normalizePath(tempdir(),winslash = "/")
#test lasts 15 sec:
library(dplyr)
library(readr)
library(ReinforcementLearning)
library(magrittr)
library(lazytrade)
data(data_trades)
x <- data_trades
rl_write_control_parameters(x = data_trades,
                            path_control_files = dir,
                            num_trades_to_consider = 20)

Author(s)

(C) 2019 Vladimir Zhbanko