From e4fca60692fe3b7671e33c43eb0e14f6e7409693 Mon Sep 17 00:00:00 2001
From: mia <mia@kieler.cc>
Date: Thu, 23 Apr 2026 10:00:43 +0200
Subject: [PATCH] Implementiere best_future_reward

---
 __pycache__/nim.cpython-313.pyc | Bin 7652 -> 7731 bytes
 nim.py                          |  16 +++++++++-------
 test.py                         |   2 ++
 3 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/__pycache__/nim.cpython-313.pyc b/__pycache__/nim.cpython-313.pyc
index 181141d67368065866b608205017271ef43af02c..af19071c92a4d1c4d5317fe1cc425c6d507b4ae2 100644
GIT binary patch
delta 732
zcmYjPUr19?82`>aySUjj_vg-GPH+AT?`RR~q8d7*q9B8Ef26_OT6b#c%5&A}lPe*7
z3gagD5J3`@Ah=i$KK58X#A4)wPX+bhQ??1^Ti;nKeenIx_nq&@_xr&)-_PfK)upPc
zO2CMH-X3{me_I{0C?d8Lv-A!j3Q@8M5rSno0;Frd9wPz$n^Dr&EKaOGSQ@XTXi5mu
zQ*dqoAT9v(lNN~ZZRH3;kaP<Dv<~hXgVY9H`}YU?T0j$I%#@IXc0=x=RUw|lp)QgQ
zm>rm<%Lv^<Gsv(AL9oFU2SADh1btkz&ju)$;i^-xD9X_11UQ1!Avi;mgtg+JoiIN?
z3{1g;c{o&YxQU=~8ClL`*inAvM%Z#+9~tYt>bb3I6NAagiAkmoGBq7%cRaq)`-%9d
z*6r~PsVQ~(0UPWd<x3h6{%k`A@=ACk{XX=jbIrTr&9<&PvL`p){*ClrS!b@{IBBQs
z23PVUY|*j!H2OMpvqkTzGpr6rWqvHC|FF4dZ(+Zefn5h!91E&$o)>q_(5Ac&Er$x$
zp5@R|B71seYF%2H)x8TH3**ncFGKScd27#(5v2MhruWT{=Z)c4+7~7KF<nr?g%e@y
z_lhR4`H99q#B+16WLPyJB=}!Ahzcxd?vs5+XyPXRnKqzD?SI$o0-r_n;o2^e(qGj6
zBys(Tv#q%auOGv%U=|yT^;GO5#mX8{Dz;RMmZB_)1LU_Sx9K!dq<=jY6NiyLm%CK&
mBQ;UJkiQH&%VAi5>T;10ea$6HF+yCwfMe+*ttD1wMaEx!jHjjm

delta 596
zcmdmN^Te9(GcPX}0}uqCd6{`ncq3n!pd>qx%M8Sy`4|}(rZPkWNeGzyfJ2Nah;{OA
zQQ67M1VtG`C+`uImnvq;V={%R$zzsdhz98g1CV+fg!WKIn6gl26DC%m5@CigmSQG-
zhGHgR1`ienhJ2R*CSNuN25trgpjaNuWI-Vjp!pC^8iOKGSe_xB(Uw`BA&pU!d9%8Z
z7NeCWOHm-utRe>>af>B8wX*mYb8cdVCTkHdNH_>2%nTGRk^*rZfJ8CKZUqH}$%P`?
z_0>Rj1H%_N24RU6ChN^snyt59X}!kwvV_kn+Xc=C7<alINZsi_TWp5#jKDc!D{U`I
z_*@q9?O^}F#LOvrM_6ou$#S!WW@}V8u&&nG!G1x@{*to8WpPI!IU{iv<3(kMi{g%#
zg`F<&IQ{&@${^{>`16st<BtzajGUr3g++ep7Ha?<u!zUejAIigkT}S!=)}NqP=(vk
zn&Y588;EVq3M3CPFgdX>Z{`&3W>Sm<>HvGBC<4d=`XBDmBA`l!qNvH+#7!A<CchDX
z&lo@Xj)a<$B2c)E;R_QFtNbS!W>#OuPh0}5qMuawSOq^R2(yZQ*V?Qq$;k{<tuK?n
zng&$exOs|<4WmFT$UI=oFcevWh_uNMWMvuCC;yXG5RGGGl>Nv6B0oDYi!%xp2?13A
E01@bm`v3p{

diff --git a/nim.py b/nim.py
index bce6111..ad1a42c 100644
--- a/nim.py
+++ b/nim.py
@@ -95,15 +95,17 @@ class NimAI():
         float: The highest Q-value among available actions. 
                Returns 0 if no actions are available.
     """
+        state = tuple(state)
         # actions = []
-        # for q in self.q.key:
-        #     if q[0] == state:
+        # for q in self.q:
+        #     print(q)
+        #     if q[0] == tuple(state):
         #         actions.append(q[1])
-        actions = tuple([key[1] for key in self.q.keys() if key[0] == state])
-        try:
-            return max([q for q in self.q[tuple(state), actions]])
-        except:
-            return 0
+        actions = [key[1] for key in self.q if key[0] == state]
+        # print(actions)
+        # print(self.q[state, action] for action in actions)
+        # print(max(self.q[state, action] for action in actions))
+        return 0 if actions == [] else max(self.q[state, action] for action in actions)
 
     def choose_action(self, state, epsilon=True):
         """
diff --git a/test.py b/test.py
index dfa2c8b..3a974b3 100644
--- a/test.py
+++ b/test.py
@@ -19,6 +19,8 @@ def test_update_q_value(ai):
 
 def test_best_future_reward(ai):
     print("\n--- Testing best_future_reward ---")
+    print(ai.best_future_reward([1,1,1,0]))
+    print(ai.best_future_reward([1,1,1,1]))
 
 
 def test_choose_action(ai):