Updated logging to wandb

cooperative_cuisine/reinforcement_learning/train_single_agent.py

@@ -44,7 +44,7 @@ def main(cfg: DictConfig):
         # also upload the environment config to W&B and all stable baselines3 hyperparams
         run = wandb.init(
             project=additional_configs["project_name"],
-            config=config,
+            config=data_to_log,
             sync_tensorboard=additional_configs["sync_tensorboard"],  # auto-upload sb3's tensorboard metrics
             monitor_gym=additional_configs["monitor_gym"],
             dir= additional_configs["log_path"]