Minor changes to tutorial notebooks

Summary: - added tutorial to list in `README.md` - there were a few unused and duplicated imports. - added backticks (``) around code and Python classes, variables, etc (as in `PearlAgent`) - added a link to nbviewer at the top of the notebooks. Here, Ive added in the next diff: > Here is a [better rendering](https://nbviewer.org/github/facebookresearch/Pearl/blob/main/tutorials/actor_critic_and_rc_safety_module/actor_critic_and_safe_actor_critic.ipynb) of this notebook on [nbviewer](https://nbviewer.org/). - moved the title and description of the tutorial to the top. Reviewed By: Yonathae Differential Revision: D54573173 fbshipit-source-id: b33bf52977594f3ebfb59354f42c4b55a3e7d200
facebookresearch · Mar 6, 2024 · c42a935 · c42a935
1 parent 126eb2d
commit c42a935
Show file tree

Hide file tree

Showing 3 changed files with 100 additions and 86 deletions.
diff --git a/README.md b/README.md
@@ -83,6 +83,7 @@ We provide a few tutorial Jupyter notebooks (and are currently working on more!)
 
 4. [Deep Q-Learning (DQN) and Double DQN](https://nbviewer.org/github/facebookresearch/Pearl/blob/main/tutorials/sequential_decision_making/DQN_and_DoubleDQN_example.ipynb). Demonstrates how to run DQN and Double DQN on the Cart-Pole environment.
 
+5. [Actor-critic algorithms with safety constraints](https://nbviewer.org/github/facebookresearch/Pearl/blob/main/tutorials/actor_critic_and_rc_safety_module/actor_critic_and_safe_actor_critic.ipynb). Demonstrates how to run Actor Critic methods, including a version with safe constraints.
 
 
 ## Design and Features

diff --git a/tutorials/actor_critic_and_rc_safety_module/actor_critic_and_safe_actor_critic.ipynb b/tutorials/actor_critic_and_rc_safety_module/actor_critic_and_safe_actor_critic.ipynb
diff --git a/tutorials/frozen_lake/frozen_lake.ipynb b/tutorials/frozen_lake/frozen_lake.ipynb
@@ -9,7 +9,7 @@
         "\n",
         "Here is a [better rendering](https://nbviewer.org/github/facebookresearch/Pearl/blob/main/tutorials/frozen_lake/frozen_lake.ipynb) of this notebook on [nbviewer](https://nbviewer.org/).\n",
         "\n",
-        "This example sho ws how to use DQN to solve the `FrozenLake-v1` environment from gymnasium. This environment has observations as indices (tabular observation)which is not suitable for learning with a neural network. In what follows, we show how to use Pearl's `OneHotObservationsFromDiscrete` wrapper to convert observations to their one-hot representations."
+        "This example shows how to use DQN to solve the `FrozenLake-v1` environment from gymnasium. This environment has observations as indices (tabular observation)which is not suitable for learning with a neural network. In what follows, we show how to use Pearl's `OneHotObservationsFromDiscrete` wrapper to convert observations to their one-hot representations."
       ]
     },
     {
@@ -1821,29 +1821,43 @@
                 "custom": {
                   "cells": [],
                   "metadata": {
-                    "accelerator": "GPU",
-                    "colab": {
-                      "gpuType": "T4",
-                      "include_colab_link": true,
-                      "provenance": []
+                    "custom": {
+                      "cells": [],
+                      "metadata": {
+                        "accelerator": "GPU",
+                        "colab": {
+                          "gpuType": "T4",
+                          "include_colab_link": true,
+                          "provenance": []
+                        },
+                        "fileHeader": "",
+                        "fileUid": "4316417e-7688-45f2-a94f-24148bfc425e",
+                        "isAdHoc": false,
+                        "kernelspec": {
+                          "display_name": "pearl (local)",
+                          "language": "python",
+                          "name": "pearl_local"
+                        },
+                        "language_info": {
+                          "name": "python"
+                        }
+                      },
+                      "nbformat": 4,
+                      "nbformat_minor": 2
                     },
                     "fileHeader": "",
-                    "fileUid": "4316417e-7688-45f2-a94f-24148bfc425e",
+                    "fileUid": "1158a851-91bb-437e-a391-aba92448f600",
+                    "indentAmount": 2,
                     "isAdHoc": false,
-                    "kernelspec": {
-                      "display_name": "pearl (local)",
-                      "language": "python",
-                      "name": "pearl_local"
-                    },
                     "language_info": {
-                      "name": "python"
+                      "name": "plaintext"
                     }
                   },
                   "nbformat": 4,
                   "nbformat_minor": 2
                 },
                 "fileHeader": "",
-                "fileUid": "1158a851-91bb-437e-a391-aba92448f600",
+                "fileUid": "ddf9fa29-09d7-404d-bc1b-62a580952524",
                 "indentAmount": 2,
                 "isAdHoc": false,
                 "language_info": {
@@ -1854,36 +1868,36 @@
               "nbformat_minor": 2
             },
             "fileHeader": "",
-            "fileUid": "ddf9fa29-09d7-404d-bc1b-62a580952524",
+            "fileUid": "e751f6fa-be9e-4f88-9fef-36812551b013",
             "indentAmount": 2,
             "isAdHoc": false,
+            "kernelspec": {
+              "display_name": "pearl2",
+              "language": "python",
+              "name": "python3"
+            },
             "language_info": {
-              "name": "plaintext"
+              "codemirror_mode": {
+                "name": "ipython",
+                "version": 3
+              },
+              "file_extension": ".py",
+              "mimetype": "text/x-python",
+              "name": "python",
+              "nbconvert_exporter": "python",
+              "pygments_lexer": "ipython3",
+              "version": "3.8.18"
             }
           },
           "nbformat": 4,
           "nbformat_minor": 2
         },
         "fileHeader": "",
-        "fileUid": "e751f6fa-be9e-4f88-9fef-36812551b013",
+        "fileUid": "a6d73a55-c990-483c-9ad3-c926ad0c935a",
         "indentAmount": 2,
         "isAdHoc": false,
-        "kernelspec": {
-          "display_name": "pearl2",
-          "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": "3.8.18"
+          "name": "plaintext"
         }
       },
       "nbformat": 4,
Original file line number	Diff line number	Diff line change
Expand Up		@@ -83,6 +83,7 @@ We provide a few tutorial Jupyter notebooks (and are currently working on more!)

		4. [Deep Q-Learning (DQN) and Double DQN](https://nbviewer.org/github/facebookresearch/Pearl/blob/main/tutorials/sequential_decision_making/DQN_and_DoubleDQN_example.ipynb). Demonstrates how to run DQN and Double DQN on the Cart-Pole environment.

		5. [Actor-critic algorithms with safety constraints](https://nbviewer.org/github/facebookresearch/Pearl/blob/main/tutorials/actor_critic_and_rc_safety_module/actor_critic_and_safe_actor_critic.ipynb). Demonstrates how to run Actor Critic methods, including a version with safe constraints.


		## Design and Features
Expand Down