integration of (legacy) training systems, initialize, train, show on the UI

This commit is contained in:
Dobromir Popov
2025-07-05 00:33:03 +03:00
parent 5ca7493708
commit d260e73f9a
10 changed files with 647 additions and 151 deletions

View File

@ -873,7 +873,7 @@ class RealtimeRLCOBTrader:
# Penalize for large predicted changes that are wrong
if predicted_direction != actual_direction and abs(predicted_change) > 0.001:
reward -= abs(predicted_change) * 2.0
# Add reward for PnL (realized or unrealized)
reward += current_pnl * 0.1 # Small reward for PnL, adjusted by a factor