Resolve "Restructure Reinforcement Learning files"

#Closes 142

cooperative_cuisine/reinforcement_learning/gym_env.py

@@ -431,13 +431,14 @@ class EnvGymWrapper(Env):
 
 
 def main():
-    Path("logs/reinforcement_learning").mkdir(exist_ok=True)
+    rl_logs = Path("logs/reinforcement_learning")
+    rl_logs.mkdir(exist_ok=True)
     rl_agent_checkpoints = Path("logs/reinforcement_learning/rl_agent_checkpoints")
     rl_agent_checkpoints.mkdir(exist_ok=True)
 
     config = {
         "policy_type": "MlpPolicy",
-        "total_timesteps": 300_000,  # hendric sagt eher so 300_000_000 schritte
+        "total_timesteps": 3_000_000,  # hendric sagt eher so 300_000_000 schritte
         "env_id": "overcooked",
         "number_envs_parallel": 64,
     }