update penalnty calculation, dynamic import of gnn (!5) · Merge requests · Eclipse Research Labs / ENACT Project / Deep Reinforced Learning Agent

Thanasis Kotsiopoulos requested to merge rl_update_v1.2 into main Dec 05, 2024

This PR contains update on how to compute the penalnty for the RL through the compute_reward() function and also use it for assessment of the matchmaking.

The compute_reward_ga() function in main.py is used only to assess the matchmaking and it is not used to update the GA.

update penalnty calculation, dynamic import of gnn

Merge request reports