└── passive learning.ipynb


/passive learning.ipynb:
--------------------------------------------------------------------------------
 1 | {
 2 |  "cells": [
 3 |   {
 4 |    "cell_type": "code",
 5 |    "execution_count": 1,
 6 |    "id": "5d951c11",
 7 |    "metadata": {},
 8 |    "outputs": [
 9 |     {
10 |      "name": "stdout",
11 |      "output_type": "stream",
12 |      "text": [
13 |       "Learned Q-values:\n",
14 |       "[[0.  0.1]\n",
15 |       " [0.1 0. ]\n",
16 |       " [0.  0.1]\n",
17 |       " [0.1 0. ]\n",
18 |       " [0.  0. ]]\n"
19 |      ]
20 |     }
21 |    ],
22 |    "source": [
23 |     "import numpy as np\n",
24 |     "\n",
25 |     "class QLearningAgent:\n",
26 |     "    def __init__(self, num_states, num_actions, learning_rate=0.1, discount_factor=0.9):\n",
27 |     "        self.num_states = num_states\n",
28 |     "        self.num_actions = num_actions\n",
29 |     "        self.learning_rate = learning_rate\n",
30 |     "        self.discount_factor = discount_factor\n",
31 |     "        self.q_table = np.zeros((num_states, num_actions))\n",
32 |     "\n",
33 |     "    def update_q_table(self, state, action, reward, next_state):\n",
34 |     "        best_next_action = np.argmax(self.q_table[next_state])\n",
35 |     "        td_target = reward + self.discount_factor * self.q_table[next_state, best_next_action]\n",
36 |     "        td_error = td_target - self.q_table[state, action]\n",
37 |     "        self.q_table[state, action] += self.learning_rate * td_error\n",
38 |     "\n",
39 |     "# Assuming we have a dataset of experiences (state, action, reward, next_state)\n",
40 |     "dataset = [(0, 1, 1, 1), (1, 0, 1, 2), (2, 1, 1, 3), (3, 0, 1, 4)]\n",
41 |     "\n",
42 |     "# Example usage:\n",
43 |     "if __name__ == \"__main__\":\n",
44 |     "    # Create Q-learning agent\n",
45 |     "    agent = QLearningAgent(num_states=5, num_actions=2)\n",
46 |     "\n",
47 |     "    # Passive learning\n",
48 |     "    for state, action, reward, next_state in dataset:\n",
49 |     "        agent.update_q_table(state, action, reward, next_state)\n",
50 |     "\n",
51 |     "    # Print learned Q-values\n",
52 |     "    print(\"Learned Q-values:\")\n",
53 |     "    print(agent.q_table)\n"
54 |    ]
55 |   }
56 |  ],
57 |  "metadata": {
58 |   "kernelspec": {
59 |    "display_name": "Python 3 (ipykernel)",
60 |    "language": "python",
61 |    "name": "python3"
62 |   },
63 |   "language_info": {
64 |    "codemirror_mode": {
65 |     "name": "ipython",
66 |     "version": 3
67 |    },
68 |    "file_extension": ".py",
69 |    "mimetype": "text/x-python",
70 |    "name": "python",
71 |    "nbconvert_exporter": "python",
72 |    "pygments_lexer": "ipython3",
73 |    "version": "3.9.12"
74 |   }
75 |  },
76 |  "nbformat": 4,
77 |  "nbformat_minor": 5
78 | }
79 | 


--------------------------------------------------------------------------------