From ee68ca8046082ad403c0107a6f1887f2f39e52bd Mon Sep 17 00:00:00 2001
From: p74035216 <p74035216@example.org>
Date: Wed, 22 Nov 2023 23:53:05 +0800
Subject: [PATCH] ADD file via upload

---
 TestRL.py | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)
 create mode 100644 TestRL.py

diff --git a/TestRL.py b/TestRL.py
new file mode 100644
index 0000000..69ec88b
--- /dev/null
+++ b/TestRL.py
@@ -0,0 +1,17 @@
+import numpy as np
+import MDP
+import RL
+
+
+''' Construct simple MDP as described in Lecture 2a Slides 13-14'''
+T = np.array([[[0.5,0.5,0,0],[0,1,0,0],[0.5,0.5,0,0],[0,1,0,0]],[[1,0,0,0],[0.5,0,0,0.5],[0.5,0,0.5,0],[0,0,0.5,0.5]]])
+R = np.array([[0,0,10,10],[0,0,10,10]])
+discount = 0.9        
+mdp = MDP.MDP(T,R,discount)
+rlProblem = RL.RL(mdp, np.random.normal)
+
+# Test Q-learning 
+[Q,policy,_] = rlProblem.qLearning(s0=0,initialQ=np.zeros([mdp.nActions,mdp.nStates]),nEpisodes=1000,nSteps=100,epsilon=0.3)
+print ("\nQ-learning results")
+print (Q)
+print (policy)
\ No newline at end of file