Make more friendly user outputs when training SB3

src/primaite/session/environment.py

@@ -37,11 +37,14 @@ class PrimaiteGymEnv(gymnasium.Env):
         terminated = False
         truncated = self.game.calculate_truncated()
         info = {}
-        print(f"Episode: {self.game.episode_counter}, Step: {self.game.step_counter}, Reward: {reward}")
         return next_obs, reward, terminated, truncated, info
 
     def reset(self, seed: Optional[int] = None) -> Tuple[ObsType, Dict[str, Any]]:
         """Reset the environment."""
+        print(
+            f"Resetting environment, episode {self.game.episode_counter}, "
+            "avg. reward: {self.game.rl_agents[0].reward_function.total_reward}"
+        )
         self.game.reset()
         state = self.game.get_sim_state()
         self.game.update_agents(state)

src/primaite/session/session.py

@@ -62,6 +62,7 @@ class PrimaiteSession:
 
     def start_session(self) -> None:
         """Commence the training/eval session."""
+        print("Staring Primaite Session")
         self.mode = SessionMode.TRAIN
         n_learn_episodes = self.training_options.n_learn_episodes
         n_eval_episodes = self.training_options.n_eval_episodes