adding trained test policies, as well as fixing evaluate script and commands

eval_experiments.py

@@ -9,13 +9,13 @@ def main(method:str='expert', folder:str=None, locations=[(0,0)], skip_running=F
         env, env_kwargs ='NRasterizedRouteIncrementingAgent', {}
     elif method in ['bc','gail']:
         env='NormalizedContinuousEvalEnv' 
-        env_kwargs={stop_on_collision:True, max_episode_steps:1000}
+        env_kwargs={'stop_on_collision':True, 'max_episode_steps':1000}
     elif method in ['hail']:
         env = 'NormalizedOptionsEvalEnv'
-        env_kwargs={stop_on_collision:True, max_episode_steps:1000}
+        env_kwargs={'stop_on_collision':True, 'max_episode_steps':1000}
     elif method in ['shail']:
         env = 'NormalizedSafeOptionsEvalEnv'
-        env_kwargs={stop_on_collision:True, max_episode_steps:1000}
+        env_kwargs={'stop_on_collision':True, 'max_episode_steps':1000}
     else:
         raise NotImplementedError
 
@@ -39,8 +39,6 @@ def main(method:str='expert', folder:str=None, locations=[(0,0)], skip_running=F
         locstr = 'loc_'+'_'.join([f'r{ro}t{tr}' for (ro,tr) in locations])
         outfolder = os.path.join('out',method,locstr)
     
-    import pdb
-    pdb.set_trace()
     # load metrics from save_path
     average_metrics = load_and_average(outfolder)
     if method in ['expert', 'idm']:

evaluate_models.sh

@@ -1,14 +1,14 @@
 # can add --skip_running if you've run before
 
 python -m eval_experiments 
-python -m eval_experiments --locations='[(0,4)]'
+python -m eval_experiments --locations='[(0,4)]' 
-python -m eval_experiments --method idm
+python -m eval_experiments --method idm 
-python -m eval_experiments --method idm --locations='[(0,4)]'
+python -m eval_experiments --method idm --locations='[(0,4)]' 
-python -m eval_experiments --method bc --folder='test_policies/bc/expA'
+python -m eval_experiments --method bc --folder='test_policies/bc/expA' 
-python -m eval_experiments --method bc --folder='test_policies/bc/expB' --locations='[(0,4)]'
+python -m eval_experiments --method bc --folder='test_policies/bc/expB' --locations='[(0,4)]' 
-python -m eval_experiments --method gail --folder='test_policies/gail/expA'
+python -m eval_experiments --method gail --folder='test_policies/gail/expA' 
-python -m eval_experiments --method gail --folder='test_policies/gail/expB'--locations='[(0,4)]'
+python -m eval_experiments --method gail --folder='test_policies/gail/expB' --locations='[(0,4)]' 
-python -m eval_experiments --method hail
+python -m eval_experiments --method hail --folder='test_policies/hail/expA'
-python -m eval_experiments --method hail --locations='[(0,4)]'
+python -m eval_experiments --method hail --folder='test_policies/hail/expB' --locations='[(0,4)]'
-python -m eval_experiments --method shail
+python -m eval_experiments --method shail --folder='test_policies/shail/expA'
-python -m eval_experiments --method shail --locations='[(0,4)]'
+python -m eval_experiments --method shail --folder='test_policies/shail/expB' --locations='[(0,4)]'