references

Author: omerbsezer

SARSA_demo.ipynb

@@ -8,6 +8,8 @@
    },
    "outputs": [],
    "source": [
+    "# Adapted from: https://github.com/lazyprogrammer/machine_learning_examples/tree/master/rl\n",
+    "# Function approximation using Q Learning\n",
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
     "from gridWorldGame import standard_grid, negative_grid,print_values, print_policy\n",

func_approx_q_learning_demo.ipynb

@@ -1,3 +1,4 @@
+# Adapted from: https://github.com/lazyprogrammer/machine_learning_examples/tree/master/rl
 import numpy as np
 
 class Grid: # Environment

gridWorldGame.py

@@ -8,6 +8,7 @@
    },
    "outputs": [],
    "source": [
+    "# Adapted from: https://github.com/lazyprogrammer/machine_learning_examples/tree/master/rl\n",
     "import numpy as np\n",
     "from gridWorldGame import standard_grid, negative_grid,print_values, print_policy\n",
     "\n",

monte_carlo_demo.ipynb

@@ -8,6 +8,7 @@
    },
    "outputs": [],
    "source": [
+    "# Adapted from: https://github.com/lazyprogrammer/machine_learning_examples/tree/master/rl\n",
     "# the Monte Carlo Epsilon-Greedy method to find the optimal policy and value function\n",
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",

monte_carlo_epsilon_greedy_demo.ipynb

@@ -8,6 +8,7 @@
    },
    "outputs": [],
    "source": [
+    "# Adapted from: https://github.com/lazyprogrammer/machine_learning_examples/tree/master/rl\n",
     "# the Monte Carlo Exploring-Starts method to find the optimal policy\n",
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",

monte_carlo_es_demo.ipynb

@@ -16,6 +16,7 @@
     }
    ],
    "source": [
+    "# Adapted from: https://github.com/lazyprogrammer/machine_learning_examples/tree/master/rl\n",
     "import numpy as np\n",
     "from gridWorldGame import standard_grid, negative_grid,print_values, print_policy\n",
     "\n",

policy_iteration_demo.ipynb

@@ -8,6 +8,7 @@
    },
    "outputs": [],
    "source": [
+    "# Adapted from: https://github.com/lazyprogrammer/machine_learning_examples/tree/master/rl\n",
     "# the Q-Learning method to find the optimal policy and value function\n",
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",

q_learning_demo.ipynb

@@ -16,7 +16,8 @@
     }
    ],
    "source": [
-    "# same as policy iteration\n",
+    "# Adapted from: https://github.com/lazyprogrammer/machine_learning_examples/tree/master/rl\n",
+    "# Value iteration\n",
     "import numpy as np\n",
     "from gridWorldGame import standard_grid, negative_grid,print_values, print_policy\n",
     "\n",