aimacode
diff --git a/‎images/-0.04.jpg
16.5 KB b/‎images/-0.04.jpg
16.5 KB
diff --git a/‎images/-0.4.jpg
19.6 KB b/‎images/-0.4.jpg
19.6 KB
diff --git a/‎images/-4.jpg
19.1 KB b/‎images/-4.jpg
19.1 KB
diff --git a/‎images/4.jpg
21 KB b/‎images/4.jpg
21 KB
diff --git a/‎images/ge0.jpg
19.8 KB b/‎images/ge0.jpg
19.8 KB
diff --git a/‎images/ge1.jpg
20.6 KB b/‎images/ge1.jpg
20.6 KB
diff --git a/‎images/ge2.jpg
25.6 KB b/‎images/ge2.jpg
25.6 KB
diff --git a/‎images/ge4.jpg
23.1 KB b/‎images/ge4.jpg
23.1 KB
diff --git a/‎images/grid_mdp.jpg
13.2 KB b/‎images/grid_mdp.jpg
13.2 KB
diff --git a/‎images/grid_mdp_agent.jpg
6.49 KB b/‎images/grid_mdp_agent.jpg
6.49 KB
diff --git a/‎mdp.ipynb
Lines changed: 1220 additions & 2 deletions b/‎mdp.ipynb
Lines changed: 1220 additions & 2 deletions
diff --git a/‎tests/test_mdp.py
Lines changed: 0 additions & 8 deletions b/‎tests/test_mdp.py
Lines changed: 0 additions & 8 deletions
@@ -70,14 +70,6 @@ def test_policy_iteration():
         (2, 1): (1, 0), (2, 2): (1, 0), (3, 0): (0, 1),
         (3, 1): None, (3, 2): None}
 
-    assert policy_iteration(sequential_decision_environment_3) == {
-        (0, 0): (-1, 0), (0, 1): (0, -1), (0, 2): (0, -1), (0, 3): (0, -1), (0, 4): None,
-        (1, 0): (-1, 0), (1, 1): (-1, 0), (1, 4): (1, 0),
-        (2, 0): (-1, 0), (2, 1): (0, -1), (2, 2): None, (2, 4): (1, 0),
-        (3, 0): (-1, 0), (3, 2): None, (3, 3): (1, 0), (3, 4): (1, 0),
-        (4, 0): (-1, 0), (4, 3): (1, 0), (4, 4): (1, 0),
-        (5, 0): None, (5, 1): (0, 1), (5, 2): (0, 1), (5, 3): (0, 1), (5, 4): (1, 0)}
-
 
 def test_best_policy():
     pi = best_policy(sequential_decision_environment,