verified working state in connect_trans* and moved the next steps from that file to README

temporaryWork
youainti 5 years ago
parent 28dcb5a359
commit 9335ce1295

@ -1,4 +1,11 @@
# COMPUTATIONAL TODO
Curently the successful_recursion needs to be changed to include the launches as a NN.
- This may include creating a launch NN function (class maybe?)
## Next steps
- implement 'launch function as a function' portion
- This will probably use a neural network as a function type approach.
- substitute the transition functions into the optimality conditions.
- use these optimality conditions to create a loss function
- add boundary conditions to loss function
- get a basic gradient descent/optimization of launch function working.
- add satellite deorbit to model.
- turn this into a framework in a module, not just a single notebook (long term goal)

@ -3,7 +3,7 @@
{
"cell_type": "code",
"execution_count": 1,
"id": "closed-glenn",
"id": "variable-telephone",
"metadata": {
"tags": []
},
@ -16,7 +16,7 @@
},
{
"cell_type": "markdown",
"id": "naval-ivory",
"id": "minimal-quarterly",
"metadata": {},
"source": [
"# Setup Functions\n",
@ -26,7 +26,7 @@
{
"cell_type": "code",
"execution_count": 2,
"id": "italian-enforcement",
"id": "instructional-guide",
"metadata": {},
"outputs": [],
"source": [
@ -73,7 +73,7 @@
},
{
"cell_type": "markdown",
"id": "fancy-tucson",
"id": "spread-humor",
"metadata": {},
"source": [
"## Setup functions related to the problem"
@ -82,7 +82,7 @@
{
"cell_type": "code",
"execution_count": 3,
"id": "outside-arrangement",
"id": "supposed-chorus",
"metadata": {},
"outputs": [],
"source": [
@ -140,7 +140,7 @@
{
"cell_type": "code",
"execution_count": 4,
"id": "romance-generation",
"id": "analyzed-drink",
"metadata": {},
"outputs": [],
"source": [
@ -207,7 +207,7 @@
},
{
"cell_type": "markdown",
"id": "fluid-parks",
"id": "martial-station",
"metadata": {},
"source": [
"# Actual calculations"
@ -216,7 +216,7 @@
{
"cell_type": "code",
"execution_count": 5,
"id": "changing-january",
"id": "ambient-breakfast",
"metadata": {},
"outputs": [],
"source": [
@ -248,7 +248,7 @@
{
"cell_type": "code",
"execution_count": 6,
"id": "dominant-boost",
"id": "deluxe-remains",
"metadata": {},
"outputs": [
{
@ -275,8 +275,8 @@
"\n",
"\n",
"\n",
"tensor([ -9855.1680, -9848.4297, -9849.5527, -9849.5527, -15547.5283,\n",
" 170308.7656], grad_fn=<MvBackward>) \n",
"tensor([ -9855.1680, -9848.4297, -9849.5527, -9849.5527, -15547.5273,\n",
" 170308.7812], grad_fn=<MvBackward>) \n",
"\n",
"\n",
"\n"
@ -292,25 +292,16 @@
},
{
"cell_type": "markdown",
"id": "unnecessary-architect",
"id": "parallel-classroom",
"metadata": {},
"source": [
"Also, maybe I can create a `Model` class that upon construction will capture the necesary constants, functions, etc.\n",
"\n",
"## Next steps\n",
"- implement 'launch function as a function' portion\n",
"- substitute the transition functions into the optimality conditions.\n",
"- use these optimality conditions to create a loss function\n",
"- add boundary conditions to loss function\n",
"- get a basic gradient descent/optimization of launch function working.\n",
"- add satellite deorbit to model.\n",
"- turn this into a framework in a module, not just a single notebook (long term goal)"
"Also, maybe I can create a `Model` class that upon construction will capture the necesary constants, functions, etc.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "varying-organization",
"id": "copyrighted-freeze",
"metadata": {},
"outputs": [],
"source": []
@ -332,7 +323,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.5"
"version": "3.8.8"
}
},
"nbformat": 4,

Loading…
Cancel
Save