Auto stash before merge of "master" and "origin/master"

.gitignore

 *pycache*
 *ppo_policy*
+
+torch_training/Nets/

torch_training/render_agent_behavior.py

 import random
 from collections import deque
 
+
+import os,sys
+root_path = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+sys.path.append(root_path)
+
 import numpy as np
 import torch
 from importlib_resources import path
@@ -87,7 +92,7 @@ action_size = 5
 
 # We set the number of episodes we would like to train on
 if 'n_trials' not in locals():
-    n_trials = 60000
+    n_trials = 6000
 max_steps = int(3 * (env.height + env.width))
 eps = 1.
 eps_end = 0.005