Skip to content

Update Q-learning Taxi-v2 notebook: #81

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Update Q-learning Taxi-v2 notebook: #81

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
108 changes: 20 additions & 88 deletions Q learning/Taxi-v2/Q Learning with OpenAI Taxi-v2 video version.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
"<br> \n",
"In this Notebook, we'll implement an agent <b>that plays OpenAI Taxi-V2.</b>\n",
"\n",
"<img src=\"taxi.png\" alt=\"Taxi\"/>\n",
"<img src=\"../../docs/assets/img/video projects/taxi.png\" alt=\"Taxi\"/>\n",
"\n",
"The goal of this game is that our agent must <b>pick up the passenger at one location and drop him off to the goal as fast as possible.</b>\n",
"\n",
Expand Down Expand Up @@ -77,23 +77,9 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/q2ZOEFAaaI0?showinfo=0\" frameborder=\"0\" allow=\"autoplay; encrypted-media\" allowfullscreen></iframe>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"outputs": [],
"source": [
"from IPython.display import HTML\n",
"HTML('<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/q2ZOEFAaaI0?showinfo=0\" frameborder=\"0\" allow=\"autoplay; encrypted-media\" allowfullscreen></iframe>')\n"
Expand All @@ -113,10 +99,8 @@
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
Expand All @@ -135,24 +119,9 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"+---------+\n",
"|\u001b[35mR\u001b[0m: | : :G|\n",
"| : : : : |\n",
"| : : : : |\n",
"| | : | : |\n",
"|\u001b[43mY\u001b[0m| : |\u001b[34;1mB\u001b[0m: |\n",
"+---------+\n",
"\n"
]
}
],
"outputs": [],
"source": [
"env = gym.make(\"Taxi-v2\")\n",
"env.render()"
Expand All @@ -169,18 +138,9 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Action size 6\n",
"State size 500\n"
]
}
],
"outputs": [],
"source": [
"action_size = env.action_space.n\n",
"print(\"Action size \", action_size)\n",
Expand All @@ -191,23 +151,9 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[0. 0. 0. 0. 0. 0.]\n",
" [0. 0. 0. 0. 0. 0.]\n",
" [0. 0. 0. 0. 0. 0.]\n",
" ...\n",
" [0. 0. 0. 0. 0. 0.]\n",
" [0. 0. 0. 0. 0. 0.]\n",
" [0. 0. 0. 0. 0. 0.]]\n"
]
}
],
"outputs": [],
"source": [
"qtable = np.zeros((state_size, action_size))\n",
"print(qtable)"
Expand All @@ -223,10 +169,8 @@
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": true
},
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"total_episodes = 50000 # Total episodes\n",
Expand Down Expand Up @@ -254,10 +198,8 @@
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": true
},
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# 2 For life or until learning is stopped\n",
Expand Down Expand Up @@ -309,17 +251,9 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Score over time: 8.2\n"
]
}
],
"outputs": [],
"source": [
"env.reset()\n",
"rewards = []\n",
Expand Down Expand Up @@ -348,15 +282,13 @@
" break\n",
" state = new_state\n",
"env.close()\n",
"print (\"Score over time: \" + str(sum(rewards)/total_test_episodes))"
"print (\"Score over time: \", np.mean(rewards))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"metadata": {},
"outputs": [],
"source": []
}
Expand All @@ -377,7 +309,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.4"
"version": "3.7.7"
}
},
"nbformat": 4,
Expand Down