Added ONNX RNN example

README.md

@@ -287,14 +287,15 @@ Additional environment supported properties and functions
 
 1.6.0
 
-* Added ONNX export colab example.
+* Added ONNX export colab example for discrete and continious action spaces. For continuous case RNN example is provided as well.
 * Improved RNNs training in continuous space, added option `zero_rnn_on_done`.
 * Added NVIDIA CuLE support: https://github.com/NVlabs/cule
 * Added player config everride. Vecenv is used for inference.
 * Fixed multi-gpu training with central value.
 * Fixed max_frames termination condition, and it's interaction with the linear learning rate: https://github.com/Denys88/rl_games/issues/212
 * Fixed "deterministic" misspelling issue.
 * Fixed Mujoco and Brax SAC configs.
+* Fixed multiagent envs statistics reporting. Fixed Starcraft2 SMAC environments.
 
 1.5.2
 

notebooks/train_and_export_onnx_example_continuous.ipynb

@@ -29,6 +29,12 @@
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "id": "yE40EhNFVszf",
+      "metadata": {
+        "id": "yE40EhNFVszf"
+      },
+      "outputs": [],
       "source": [
         "from rl_games.torch_runner import Runner\n",
         "import os\n",
@@ -41,13 +47,7 @@
         "import onnx\n",
         "import onnxruntime as ort\n",
         "%matplotlib inline"
-      ],
-      "metadata": {
-        "id": "yE40EhNFVszf"
-      },
-      "id": "yE40EhNFVszf",
-      "execution_count": null,
-      "outputs": []
+      ]
     },
     {
       "cell_type": "code",
@@ -63,27 +63,27 @@
     },
     {
       "cell_type": "code",
-      "source": [
-        "%load_ext tensorboard"
-      ],
+      "execution_count": null,
+      "id": "2enRAdp8WrJV",
       "metadata": {
         "id": "2enRAdp8WrJV"
       },
-      "id": "2enRAdp8WrJV",
-      "execution_count": null,
-      "outputs": []
+      "outputs": [],
+      "source": [
+        "%load_ext tensorboard"
+      ]
     },
     {
       "cell_type": "code",
-      "source": [
-        "%tensorboard --logdir 'runs/'"
-      ],
+      "execution_count": null,
+      "id": "JGE4eeUCWsss",
       "metadata": {
         "id": "JGE4eeUCWsss"
       },
-      "id": "JGE4eeUCWsss",
-      "execution_count": null,
-      "outputs": []
+      "outputs": [],
+      "source": [
+        "%tensorboard --logdir 'runs/'"
+      ]
     },
     {
       "cell_type": "code",
@@ -284,31 +284,15 @@
         "print(total_reward, num_steps)\n",
         "ipythondisplay.clear_output(wait=True)"
       ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "2ae5a74c",
-      "metadata": {
-        "id": "2ae5a74c"
-      },
-      "outputs": [],
-      "source": []
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "0b5cb601",
-      "metadata": {
-        "id": "0b5cb601"
-      },
-      "outputs": [],
-      "source": []
     }
   ],
   "metadata": {
+    "accelerator": "GPU",
+    "colab": {
+      "provenance": []
+    },
     "kernelspec": {
-      "display_name": "Python 3",
+      "display_name": "warp39",
       "language": "python",
       "name": "python3"
     },
@@ -322,13 +306,14 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.9.12"
-    },
-    "colab": {
-      "provenance": []
+      "version": "3.9.13"
     },
-    "accelerator": "GPU"
+    "vscode": {
+      "interpreter": {
+        "hash": "20dffcfa027a5ca97c32e660f6348a5dd89a4a8771672beb12fd55712d57511e"
+      }
+    }
   },
   "nbformat": 4,
   "nbformat_minor": 5
-}
+}