Skip to content
Open
Changes from all commits
Commits
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
59 changes: 27 additions & 32 deletions practicals/RL_2023_prac.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -182,6 +182,8 @@
"\n",
">>>>[Build your own DQN!](#scrollTo=DN4gEJXabSvA)\n",
"\n",
">>[Beyond Discrete Actions - Policy Gradient Methods (Homework)](#scrollTo=G--a37gzd214)\n",
"\n",
">>[Conclusion](#scrollTo=fV3YG7QOZD-B)\n",
"\n",
">>[Feedback](#scrollTo=o1ndpYE50BpG)\n",
Expand Down Expand Up @@ -219,11 +221,7 @@
"execution_count": null,
"metadata": {
"cellView": "form",
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "YBdDHcI_ArCR",
"outputId": "d54005ef-e8d4-4f04-df58-807c5682912f"
"id": "YBdDHcI_ArCR"
},
"outputs": [],
"source": [
Expand Down Expand Up @@ -853,11 +851,7 @@
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "3-c9WC0VksSE",
"outputId": "da250547-844b-422b-828d-4aa277fc6508"
"id": "3-c9WC0VksSE"
},
"outputs": [],
"source": [
Expand Down Expand Up @@ -891,11 +885,7 @@
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "VpyHyC72mdLR",
"outputId": "9a8869f9-9955-4560-a327-d6ec00a9675a"
"id": "VpyHyC72mdLR"
},
"outputs": [],
"source": [
Expand Down Expand Up @@ -958,11 +948,7 @@
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "w5WIsxQ8lrrt",
"outputId": "a9fef971-16c8-405a-fc55-de0597a0577f"
"id": "w5WIsxQ8lrrt"
},
"outputs": [],
"source": [
Expand Down Expand Up @@ -1290,11 +1276,7 @@
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "DFMkiQVlzpHS",
"outputId": "3df6502b-2c45-4507-d2ff-faca57e8bd9e"
"id": "DFMkiQVlzpHS"
},
"outputs": [],
"source": [
Expand Down Expand Up @@ -1348,12 +1330,7 @@
"execution_count": null,
"metadata": {
"cellView": "form",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 421
},
"id": "5yaXB8MgzsWR",
"outputId": "a5c75485-cea2-43b1-d731-6151e1e065c5"
"id": "5yaXB8MgzsWR"
},
"outputs": [],
"source": [
Expand Down Expand Up @@ -3664,6 +3641,24 @@
"\"\"\" % data_url)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "G--a37gzd214"
},
"source": [
"## Beyond Discrete Actions - Policy Gradient Methods (Homework)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "PS6JUPeed214"
},
"source": [
"We have only covered a very limited set of reinforcement learning methods. If you would like to learn about a whole other family of techniques (on which current state of the art methods are based) please have a look at the practical from 2022 [here](https://colab.research.google.com/github/deep-learning-indaba/indaba-pracs-2022/blob/main/practicals/introduction_to_reinforcement_learning.ipynb)."
]
},
{
"cell_type": "markdown",
"metadata": {
Expand Down Expand Up @@ -3775,4 +3770,4 @@
},
"nbformat": 4,
"nbformat_minor": 0
}
}