From 933d0c5d277f70dbf3ec6926351bc2511dab5e3f Mon Sep 17 00:00:00 2001
From: mia <mia@kieler.cc>
Date: Thu, 23 Apr 2026 09:39:16 +0200
Subject: [PATCH] Implementiere update_q_value

---
 __pycache__/nim.cpython-313.pyc | Bin 7495 -> 7652 bytes
 nim.py                          |  12 +++++++++---
 test.py                         |   5 +++++
 3 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/__pycache__/nim.cpython-313.pyc b/__pycache__/nim.cpython-313.pyc
index 90658617e3ea63406224a7e1b64888db1983f157..181141d67368065866b608205017271ef43af02c 100644
GIT binary patch
delta 743
zcmX?Z^~9R@GcPX}0}uqCd6{`{BX2(k<EF`TIpUduStmc>5NBso2g$L6*o+*Le{jgx
zbNZ#vnh63o?KPQJvJ{B`6(A8zK<-MWA`k@@O+R}E1l|A@7uf&>ffQUvdKwr!L&&{E
z=z~~t5-6w1Qe+1+u813~8?4NBayX|Nn<GfdX>v2CR!}IA*}!l|P;|0b2TKpz2Mz``
z%?_4+wobMS{E8Pjly0bM5YPR<#vmrW`7Wn1Bcs7)L2gziMu*AbyxJ13Kuc~3`eo)i
zdg`U8mc$pvmnG(urkZY!;$6<94RH;~Ne&<)5J+gU74d@DK_Eg8M0kS;ugN+Ba*Xbi
zy#*v0-8ZKSEM$rUsRrx2#gd&`S$vB*H?cyK6`}hUGf=ol3Z|-<706Nmfg*m8m>ZC|
zB>{0+QfhHYd|GKqX;Er?QEGW&QA+sc6k#1^1F#(|Amwr(A`(P6fQSen0Ssw`Q=LGf
zQIijdnKI@~{w6k89@TGtnoQ|H6+rO79vr2Uw~5P(`U3eypdc!82N57A6~#|}C9cQH
z!z%wtX0xosZ6;YnNZ5kp;oO)1fnc(Xw3=u<NSqr)7=Q>K5aByHTv~-2uDHl^a+|aw
kW8>x((l(5Yv6G+5_=?6cGRl5r0Fj>^n8g`|iiCg~0f8;A`~Uy|

delta 668
zcmaE2ecX!oGcPX}0}#AQy`HJJk++|Nv25~Oj`-*ZfgC1~I0!^2<S;{63=HWEnyh{=
z{{w+0(@K^ikQxN>62#SHDq;nR+5w4|AhUr2wn*Y4lkak>u{nX1I8Wx}(lRgxG8-7~
z2#QV?>tN|&yP>Yx!P3vx$##KX`67o38ux*y)aF($V@5`;%{#eSnHU`>@8{K)a041~
zOVBSf*U?iiJ+&mhFup7?r!-Z6GZWu(rWA->APXHqL=ceBWGmtYv4cT`9*FP(5#B)J
z7DrlXNoi4Pd|@#gkgEU&Mf@OX50JD7#G2BAl*AICB8W|nn|TEnGC6>Z23vBAB|EjU
z_!e_+VudCv!m3-$K;a@On5tq>Kp~m$KKY%nEMwqi9uXa81F%^vAf<93A_}IdC=$rh
zWI-5O<P4IEo}3|W%9u8Jp7>m4R1f=UGNl7m0Ko(M^jR}OV5j}$C<%E{KcH9<DD1#K
zD{=?15+?Ua=&`b~%6}5rd{E*xlL|bDfbj^5-y#tZ0T(T@0dgnrlvWc>0Eu&h2m=to
z10wt;f00(<Mkw~0tSqC*SiRX*#)gqGZgP{XuV@4#qwGfp5c#=;Nt{urNC>DA0P2L1
A%m4rY

diff --git a/nim.py b/nim.py
index 8056c8b..bce6111 100644
--- a/nim.py
+++ b/nim.py
@@ -31,10 +31,16 @@ class Nim():
 
 
 class NimAI():
-    def __init__(self, alpha=0.5, epsilon=0.1):
+    def __init__(self, alpha=0.5, epsilon=1):
         self.q = dict()  # Q-value table
-        self.q[(0, 0, 0, 2), (3, 2)] = -1 # Test Q-Value 
-        self.q[(0, 0, 0, 2), (3, 1)] = 10 # Test Q-Value 
+        # self.q[(0, 0, 0, 2), (3, 2)] = -1 # Test Q-Value 
+        # self.q[(0, 0, 0, 2), (3, 1)] = 10 # Test Q-Value 
+        
+        self.q[((1,1,1,0), (0,1))] = 0.4
+        self.q[((1,1,1,0), (1,1))] = 0.9
+        self.q[((1,1,1,0), (2,1))] = 0.7
+        self.q[((2,1,1,0), (0,1))] = 0.2
+
         
         self.alpha = alpha  # Learning rate
         self.epsilon = epsilon  # Exploration rate
diff --git a/test.py b/test.py
index 0731673..dfa2c8b 100644
--- a/test.py
+++ b/test.py
@@ -10,6 +10,11 @@ def test_get_q_value(ai):
 
 def test_update_q_value(ai):
     print("\n--- Testing update_q_value ---")
+    state = (2, 1, 1, 0)
+    action = (0, 1)
+    print(ai.q)
+    print(ai.update_q_value([2, 1, 1, 0], (0, 1), 0.2, 1, 0.8))
+    print(ai.q)
 
 
 def test_best_future_reward(ai):