debug : nan, it's the learning rate too high,s try to find optimum: 0.001

This commit is contained in:
2025-12-13 05:00:23 +01:00
parent 32207170f6
commit 3d54639d4c
18 changed files with 834 additions and 148 deletions
@@ -99,7 +99,7 @@ struct RL_agent {
};
struct networks_qlearning * create_nework_qlearning(
struct networks_qlearning * create_network_qlearning(
struct config_layers * config,
bool randomize, float minR, float maxR, int randomRange,
size_t nb_prod_thread,