Fixed policy evaluation for autoregressive

src/training_scripts/autoregressive_quantiles.py

@@ -49,7 +49,7 @@ data_processor.set_full_day_skip(False)
 
 
 #### Hyperparameters ####
-data_processor.set_output_size(96)
+data_processor.set_output_size(1)
 inputDim = data_processor.get_input_size()
 epochs = 300
 
@@ -80,7 +80,7 @@ time_embedding = TimeEmbedding(
 # lstm_model = GRUModel(time_embedding.output_dim(inputDim), len(quantiles), hidden_size=model_parameters["hidden_size"], num_layers=model_parameters["num_layers"], dropout=model_parameters["dropout"])
 non_linear_model = NonLinearRegression(
     time_embedding.output_dim(inputDim),
-    len(quantiles) * 96,
+    len(quantiles),
     hiddenSize=model_parameters["hidden_size"],
     numLayers=model_parameters["num_layers"],
     dropout=model_parameters["dropout"],
@@ -97,18 +97,7 @@ baseline_policy = BaselinePolicy(battery, data_path="")
 policy_evaluator = PolicyEvaluator(baseline_policy, task)
 
 #### Trainer ####
-# trainer = AutoRegressiveQuantileTrainer(
-#     model,
-#     inputDim,
-#     optimizer,
-#     data_processor,
-#     quantiles,
-#     "cuda",
-#     policy_evaluator=policy_evaluator,
-#     debug=False,
-# )
-
-trainer = NonAutoRegressiveQuantileRegression(
+trainer = AutoRegressiveQuantileTrainer(
     model,
     inputDim,
     optimizer,
@@ -119,6 +108,17 @@ trainer = NonAutoRegressiveQuantileRegression(
     debug=False,
 )
 
+# trainer = NonAutoRegressiveQuantileRegression(
+#     model,
+#     inputDim,
+#     optimizer,
+#     data_processor,
+#     quantiles,
+#     "cuda",
+#     policy_evaluator=policy_evaluator,
+#     debug=False,
+# )
+
 trainer.add_metrics_to_track(
     [PinballLoss(quantiles), MSELoss(), L1Loss(), CRPSLoss(quantiles)]
 )