From 54a12d2dde714ebf2c7fd88274673c7c20c2ac3c Mon Sep 17 00:00:00 2001 From: Vittus Mikiassen Date: Tue, 23 Jun 2026 20:44:12 +0200 Subject: [PATCH] Change OHLC data source from Kaggle to Dukascopy Updated data source reference for OHLC data in README. --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 1bf2be2..f5f59ad 100644 --- a/README.md +++ b/README.md @@ -6,7 +6,7 @@ The bot combines an LSTM neural network for sequence learning with Proximal Poli Unlike traditional bots that rely on fixed rules, the PPO agent learns when to Buy, Sell or Hold from thousands of market examples. -The program should be in a folder or the desktop where the 5m csv file with OHLC data from https://www.kaggle.com/datasets/novandraanugrah/xauusd-gold-price-historical-data-2004-2024 is, in training it will then make a LSTM-PPO-saves folder where the training is saved (used for making decisions, also in testing). +The program should be in a folder or the desktop where the 5m csv file with OHLC data downloaded from dukascopy, 3 years. is, in training it will then make a LSTM-PPO-saves folder where the training is saved (used for making decisions, also in testing). ---