80 lines
1.5 KiB
Plaintext
80 lines
1.5 KiB
Plaintext
![]() |
{
|
||
|
"cells": [
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": 33,
|
||
|
"metadata": {},
|
||
|
"outputs": [
|
||
|
{
|
||
|
"name": "stdout",
|
||
|
"output_type": "stream",
|
||
|
"text": [
|
||
|
"[0 1]\n",
|
||
|
"[1 0]\n"
|
||
|
]
|
||
|
}
|
||
|
],
|
||
|
"source": [
|
||
|
"import numpy as np\n",
|
||
|
"\n",
|
||
|
"y_out = [[[-0.52742714, -0.8918941 , -0.53989583, -0.874211 ]]]\n",
|
||
|
"\n",
|
||
|
"outputs = y_out[0][0]\n",
|
||
|
"\n",
|
||
|
"prob_action1 = outputs[:2]\n",
|
||
|
"prob_action2 = outputs[2:]\n",
|
||
|
"\n",
|
||
|
"norm_action1 = [float(i)/sum(prob_action1) for i in prob_action1]\n",
|
||
|
"norm_action2 = [float(i)/sum(prob_action2) for i in prob_action2]\n",
|
||
|
"\n",
|
||
|
"action1 = np.random.multinomial(1,norm_action1)\n",
|
||
|
"action2 = np.random.multinomial(1,norm_action2)\n",
|
||
|
"print(action1)\n",
|
||
|
"print(action2)"
|
||
|
]
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": null,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": []
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": null,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": []
|
||
|
},
|
||
|
{
|
||
|
"cell_type": "code",
|
||
|
"execution_count": null,
|
||
|
"metadata": {},
|
||
|
"outputs": [],
|
||
|
"source": []
|
||
|
}
|
||
|
],
|
||
|
"metadata": {
|
||
|
"kernelspec": {
|
||
|
"display_name": "Python 3",
|
||
|
"language": "python",
|
||
|
"name": "python3"
|
||
|
},
|
||
|
"language_info": {
|
||
|
"codemirror_mode": {
|
||
|
"name": "ipython",
|
||
|
"version": 3
|
||
|
},
|
||
|
"file_extension": ".py",
|
||
|
"mimetype": "text/x-python",
|
||
|
"name": "python",
|
||
|
"nbconvert_exporter": "python",
|
||
|
"pygments_lexer": "ipython3",
|
||
|
"version": "3.6.7"
|
||
|
}
|
||
|
},
|
||
|
"nbformat": 4,
|
||
|
"nbformat_minor": 2
|
||
|
}
|