Resolve "Restructure Reinforcement Learning files"

#Closes 142

cooperative_cuisine/reinforcement_learning/config/additional_configs/additional_config_base.yaml

+order_generator: "random_orders.yaml"
+# Here the filename of the converter should be given. The converter class needs to be called StateConverter and implement the abstract StateToObservationConverter class
+state_converter:
+  _target_: "cooperative_cuisine.reinforcement_learning.obs_converter.base_converter_onehot.BaseStateConverterOnehot"
+log_path: "logs/reinforcement_learning"
+checkpoint_path: "rl_agent_checkpoints"
+render_mode: "rgb_array"
+project_name: "overcooked"
+debug_mode: False
+vec_env: True
+sync_tensorboard: True  # auto-upload sb3's tensorboard metrics
+monitor_gym: True
+video_save_path: "logs/reinforcement_learning/videos/"
+record_video_trigger: 200_000
+video_length: 300
+save_freq: 50_000
+save_path_callback: "logs"
+name_prefix_callback: "rl_model"
+save_replay_buffer: True
+save_vecnormalize: True
+progress_bar: True
\ No newline at end of file