DeepReinforcementLearning · altaykerem · Sep 10, 2026
diff --git a/.gitignore b/.gitignore
@@ -57,16 +57,18 @@ venv.bak/
 archive/
 Chapter\ 2/Ch2_Bandits_TensorFlow.ipynb
 Chapter\ 2/Ch2_MDPs_old.ipynb
-Chapter\ 2/.ipynb_checkpoints
-Chapter\ 3/.ipynb_checkpoints/
-Chapter\ 3/.DS_Store
 Chapter\ 3/Ch3_DQN_old.ipynb
 Chapter\ 3/Ch3_Gridworld_exp.ipynb
 Chapter\ 3/Ch3_Gridworld.ipynb
 Chapter\ 3/Sokoban.py
 Chapter\ 4/Ch4_PolicyGradients_.ipynb
-Chapter\ 4/.ipynb_checkpoints
+!Chapter\ 9/MAgent/build/render/README.txt
 Sandbox
 .idea
 **/.DS_Store
 
+# Data
+data
+
+# Model files
+**.pth
diff --git a/.idea/vcs.xml b/.idea/vcs.xml
diff --git a/Appendix/Appendix.ipynb b/Appendix/Appendix.ipynb
diff --git a/Chapter 1/Ch1_Introduction.ipynb b/Chapter 1/Ch1_Introduction.ipynb
@@ -53,7 +53,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "mem = {0:0, 1:1}\n",
+    "mem = {0: 0, 1: 1}\n",
+    "\n",
     "\n",
     "def fib_mem(n):\n",
     "    if n not in mem:\n",
@@ -97,7 +98,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "4.4 s ± 844 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
+      "1.31 s ± 5.53 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
      ]
     }
    ],
@@ -115,7 +116,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "319 ns ± 274 ns per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
+      "257 ns ± 226 ns per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
      ]
     }
    ],
@@ -148,7 +149,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.14.6"
   }
  },
  "nbformat": 4,

diff --git a/Chapter 10/Ch10_book.ipynb b/Chapter 10/Ch10_book.ipynb
diff --git a/Chapter 2/Ch2_book.ipynb b/Chapter 2/Ch2_book.ipynb
diff --git a/Chapter 3/Ch3_book.ipynb b/Chapter 3/Ch3_book.ipynb
diff --git a/Chapter 3/GridBoard.py b/Chapter 3/GridBoard.py
diff --git a/Chapter 3/Gridworld.py b/Chapter 3/Gridworld.py