BUG FIXES: moving around when policy is loaded, adding BaseAlgorithm abstract classes, correcting metrics, normalizng actions if idm environment is a normalized action one, manually updating environment graph when using idm, implementing idm forward class

evaluate_models.sh

@@ -0,0 +1,16 @@
+# eval_main inputs
+# locations: List[Tuple[int,int]]= [(0,0)],
+# method: str='expert', 
+# policy_file: str='', 
+# policy_kwargs: dict={},
+# env: str='NRasterizedRouteIncrementingAgent', 
+# env_kwargs: dict={},
+# seed: int=0
+
+# expert
+python -m src.eval_main
+
+# idm
+python -m src.eval_main --method=idm
+
+