Merge branch 'main' into fix-empty-market-results-warning

assume/common/outputs.py

@@ -93,10 +93,6 @@ def __init__(
             if episode.isdigit():
                 self.episode = int(episode)
 
-            # check if episode=0 and delete all similar runs
-            if self.episode == 0:
-                self.delete_similar_runs()
-
         # construct all timeframe under which hourly values are written to excel and db
         self.start = start
         self.end = end
@@ -202,6 +198,11 @@ def on_ready(self):
             self.db = create_engine(self.db_uri)
         if self.db is not None:
             self.delete_db_scenario(self.simulation_id)
+
+            # check if episode equals 1 and delete all similar runs
+            if self.episode == 1:
+                self.delete_similar_runs()
+
         if self.save_frequency_hours is not None:
             recurrency_task = rr.rrule(
                 freq=rr.HOURLY,

assume/scenario/loader_csv.py

@@ -536,8 +536,8 @@ def setup_world(
     study_case: str,
     perform_evaluation: bool = False,
     terminate_learning: bool = False,
-    episode: int = 0,
-    eval_episode: int = 0,
+    episode: int = 1,
+    eval_episode: int = 1,
 ) -> None:
     """
     Load a scenario from a given path.
@@ -550,8 +550,8 @@ def setup_world(
         study_case (str): The specific study case within the scenario to be loaded.
         perform_evaluation (bool, optional): A flag indicating whether evaluation should be performed. Defaults to False.
         terminate_learning (bool, optional): An automatically set flag indicating that we terminated the learning process now, either because we reach the end of the episode iteration or because we triggered an early stopping.
-        episode (int, optional): The episode number for learning. Defaults to 0.
-        eval_episode (int, optional): The episode number for evaluation. Defaults to 0.
+        episode (int, optional): The episode number for learning. Defaults to 1.
+        eval_episode (int, optional): The episode number for evaluation. Defaults to 1.
 
     Raises:
         ValueError: If the specified scenario or study case is not found in the provided inputs.
@@ -726,10 +726,6 @@ def load_scenario_folder(
     inputs_path: str,
     scenario: str,
     study_case: str,
-    perform_evaluation: bool = False,
-    terminate_learning: bool = False,
-    episode: int = 1,
-    eval_episode: int = 1,
 ):
     """
     Load a scenario from a given path.
@@ -741,29 +737,12 @@ def load_scenario_folder(
         inputs_path (str): The path to the folder containing input files necessary for the scenario.
         scenario (str): The name of the scenario to be loaded.
         study_case (str): The specific study case within the scenario to be loaded.
-        perform_evaluation (bool, optional): A flag indicating whether evaluation should be performed. Defaults to False.
-        terminate_learning (bool, optional): An automatically set flag indicating that we terminated the learning process now, either because we reach the end of the episode iteration or because we triggered an early stopping.
-        episode (int, optional): The episode number for learning. Defaults to 0.
-        eval_episode (int, optional): The episode number for evaluation. Defaults to 0.
 
     Raises:
         ValueError: If the specified scenario or study case is not found in the provided inputs.
 
-    Example:
-        >>> load_scenario_folder(
-            world=world,
-            inputs_path="/path/to/inputs",
-            scenario="scenario_name",
-            study_case="study_case_name",
-            perform_evaluation=False,
-            episode=1,
-            eval_episode=1,
-            trained_policies_save_path="",
-        )
-
     Notes:
         - The function sets up the world environment based on the provided inputs and configuration files.
-        - If `perform_evaluation` is set to True, the function performs evaluation using the specified evaluation episode number.
         - The function utilizes the specified inputs to configure the simulation environment, including market parameters, unit operators, and forecasting data.
         - After calling this function, the world environment is prepared for further simulation and analysis.
 
@@ -776,10 +755,6 @@ def load_scenario_folder(
         world=world,
         scenario_data=scenario_data,
         study_case=study_case,
-        perform_evaluation=perform_evaluation,
-        terminate_learning=terminate_learning,
-        episode=episode,
-        eval_episode=eval_episode,
     )
 
 
@@ -878,7 +853,6 @@ def run_learning(
     # initialize policies already here to set the obs_dim and act_dim in the learning role
     actors_and_critics = None
     world.learning_role.initialize_policy(actors_and_critics=actors_and_critics)
-    world.output_role.delete_similar_runs()
 
     # check if we already stored policies for this simulation
     save_path = world.learning_config["trained_policies_save_path"]
@@ -928,14 +902,12 @@ def run_learning(
         range(1, world.learning_role.training_episodes + 1),
         desc="Training Episodes",
     ):
-        # TODO normally, loading twice should not create issues, somehow a scheduling issue is raised currently
-        if episode != 1:
-            setup_world(
-                world=world,
-                scenario_data=scenario_data,
-                study_case=study_case,
-                episode=episode,
-            )
+        setup_world(
+            world=world,
+            scenario_data=scenario_data,
+            study_case=study_case,
+            episode=episode,
+        )
 
         # -----------------------------------------
         # Give the newly initialized learning role the needed information across episodes
@@ -993,13 +965,12 @@ def run_learning(
 
         world.reset()
 
-        # if at end of simulation save last policies
-        if episode == (world.learning_role.training_episodes):
-            world.learning_role.rl_algorithm.save_params(
-                directory=f"{world.learning_role.trained_policies_save_path}/last_policies"
-            )
+    # save the last policies at the end of the training
+    world.learning_role.rl_algorithm.save_params(
+        directory=f"{world.learning_role.trained_policies_save_path}/last_policies"
+    )
 
-        # container shutdown implicitly with new initialisation
+    # container shutdown implicitly with new initialisation
     logger.info("################")
     logger.info("Training finished, Start evaluation run")
     world.export_csv_path = temp_csv_path

assume_cli/cli.py

@@ -127,12 +127,13 @@ def cli(args=None):
     warnings.filterwarnings("ignore", "coroutine.*?was never awaited.*")
     logging.getLogger("asyncio").setLevel("FATAL")
 
-    try:
-        # import package after argcomplete.autocomplete
-        # to improve autocompletion speed
-        from assume import World
-        from assume.scenario.loader_csv import load_scenario_folder, run_learning
+    # import package after argcomplete.autocomplete
+    # to improve autocompletion speed
+    from assume import World
+    from assume.common.exceptions import AssumeException
+    from assume.scenario.loader_csv import load_scenario_folder, run_learning
 
+    try:
         os.makedirs("./examples/local_db", exist_ok=True)
 
         if args.parallel:
@@ -169,6 +170,8 @@ def cli(args=None):
 
     except KeyboardInterrupt:
         pass
+    except AssumeException as e:
+        logging.error(f"Stopping: {e}")
     except Exception:
         logging.exception("Simulation aborted")
 

examples/notebooks/04_reinforcement_learning_algorithm_example.ipynb

@@ -311,13 +311,12 @@
     "        range(1, world.learning_role.training_episodes + 1),\n",
     "        desc=\"Training Episodes\",\n",
     "    ):\n",
-    "        if episode != 1:\n",
-    "            setup_world(\n",
-    "                world=world,\n",
-    "                scenario_data=scenario_data,\n",
-    "                study_case=study_case,\n",
-    "                episode=episode,\n",
-    "            )\n",
+    "        setup_world(\n",
+    "            world=world,\n",
+    "            scenario_data=scenario_data,\n",
+    "            study_case=study_case,\n",
+    "            episode=episode,\n",
+    "        )\n",
     "\n",
     "        # Give the newly initialized learning role the needed information across episodes\n",
     "        world.learning_role.load_inter_episodic_data(inter_episodic_data)\n",
@@ -370,16 +369,15 @@
     "\n",
     "        world.reset()\n",
     "\n",
-    "        # -----------------------------------------\n",
-    "        # 4 - Terminate Learning and Save policies\n",
+    "    # -----------------------------------------\n",
+    "    # 4 - Terminate Learning and Save policies\n",
     "\n",
-    "        # if at end of simulation save last policies\n",
-    "        if episode == (world.learning_role.training_episodes):\n",
-    "            world.learning_role.rl_algorithm.save_params(\n",
-    "                directory=f\"{world.learning_role.trained_policies_save_path}/last_policies\"\n",
-    "            )\n",
+    "    # if at end of simulation save last policies\n",
+    "    world.learning_role.rl_algorithm.save_params(\n",
+    "        directory=f\"{world.learning_role.trained_policies_save_path}/last_policies\"\n",
+    "    )\n",
     "\n",
-    "        # container shutdown implicitly with new initialisation\n",
+    "    # container shutdown implicitly with new initialisation\n",
     "    logger.info(\"################\")\n",
     "    logger.info(\"Training finished, Start evaluation run\")\n",
     "    world.export_csv_path = temp_csv_path\n",

examples/notebooks/09_example_Sim_and_xRL.ipynb

@@ -578,14 +578,12 @@
     "        range(1, world.learning_role.training_episodes + 1),\n",
     "        desc=\"Training Episodes\",\n",
     "    ):\n",
-    "        # TODO normally, loading twice should not create issues, somehow a scheduling issue is raised currently\n",
-    "        if episode != 1:\n",
-    "            setup_world(\n",
-    "                world=world,\n",
-    "                scenario_data=scenario_data,\n",
-    "                study_case=study_case,\n",
-    "                episode=episode,\n",
-    "            )\n",
+    "        setup_world(\n",
+    "            world=world,\n",
+    "            scenario_data=scenario_data,\n",
+    "            study_case=study_case,\n",
+    "            episode=episode,\n",
+    "        )\n",
     "\n",
     "        # -----------------------------------------\n",
     "        # Give the newly initialized learning role the needed information across episodes\n",