Automated tutorials push

Author: pytorchbot

_downloads/3195443a0ced3cabc0ad643537bdb5cd/introyt1_tutorial.ipynb

@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "8c435514",
+   "id": "ad604f57",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "1fb16197",
+   "id": "bdb8ea62",
    "metadata": {},
    "source": [
     "\n",

_downloads/4355e2cef7d17548f1e25f97a62828c4/template_tutorial.ipynb

@@ -31,7 +31,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f9d9dd42",
+   "id": "6c25900f",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -47,7 +47,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b1c29b13",
+   "id": "b7b47ae0",
    "metadata": {},
    "source": [
     "\n",

_downloads/63a0f0fc7b3ffb15d3a5ac8db3d521ee/tensors_deeper_tutorial.ipynb

@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a3abe643",
+   "id": "d1f2da11",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "3ebb3836",
+   "id": "27800b50",
    "metadata": {},
    "source": [
     "\n",

_downloads/6ea0e49c7d0da2713588ef1a3b64eb35/reinforcement_q_learning.py

@@ -92,6 +92,24 @@
 )
 
 
+# To ensure reproducibility during training, you can fix the random seeds
+# by uncommenting the lines below. This makes the results consistent across
+# runs, which is helpful for debugging or comparing different approaches.
+#
+# That said, allowing randomness can be beneficial in practice, as it lets
+# the model explore different training trajectories.
+
+
+# seed = 42
+# random.seed(seed)
+# torch.manual_seed(seed)
+# env.reset(seed=seed)
+# env.action_space.seed(seed)
+# env.observation_space.seed(seed)
+# if torch.cuda.is_available(): 
+#     torch.cuda.manual_seed(seed)
+
+
 ######################################################################
 # Replay Memory
 # -------------
@@ -253,13 +271,15 @@ def forward(self, x):
 # EPS_DECAY controls the rate of exponential decay of epsilon, higher means a slower decay
 # TAU is the update rate of the target network
 # LR is the learning rate of the ``AdamW`` optimizer
+
 BATCH_SIZE = 128
 GAMMA = 0.99
 EPS_START = 0.9
-EPS_END = 0.05
-EPS_DECAY = 1000
+EPS_END = 0.01
+EPS_DECAY = 2500
 TAU = 0.005
-LR = 1e-4
+LR = 3e-4
+
 
 # Get number of actions from gym action space
 n_actions = env.action_space.n

_downloads/770632dd3941d2a51b831c52ded57aa2/trainingyt.ipynb

@@ -35,7 +35,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "49ddae15",
+   "id": "819011af",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "55d88584",
+   "id": "e43a9627",
    "metadata": {},
    "source": [
     "\n",

_downloads/9da0471a9eeb2351a488cd4b44fc6bbf/reinforcement_q_learning.ipynb

@@ -111,7 +111,25 @@
     "    \"cuda\" if torch.cuda.is_available() else\n",
     "    \"mps\" if torch.backends.mps.is_available() else\n",
     "    \"cpu\"\n",
-    ")"
+    ")\n",
+    "\n",
+    "\n",
+    "# To ensure reproducibility during training, you can fix the random seeds\n",
+    "# by uncommenting the lines below. This makes the results consistent across\n",
+    "# runs, which is helpful for debugging or comparing different approaches.\n",
+    "#\n",
+    "# That said, allowing randomness can be beneficial in practice, as it lets\n",
+    "# the model explore different training trajectories.\n",
+    "\n",
+    "\n",
+    "# seed = 42\n",
+    "# random.seed(seed)\n",
+    "# torch.manual_seed(seed)\n",
+    "# env.reset(seed=seed)\n",
+    "# env.action_space.seed(seed)\n",
+    "# env.observation_space.seed(seed)\n",
+    "# if torch.cuda.is_available(): \n",
+    "#     torch.cuda.manual_seed(seed)"
    ]
   },
   {
@@ -304,13 +322,15 @@
     "# EPS_DECAY controls the rate of exponential decay of epsilon, higher means a slower decay\n",
     "# TAU is the update rate of the target network\n",
     "# LR is the learning rate of the ``AdamW`` optimizer\n",
+    "\n",
     "BATCH_SIZE = 128\n",
     "GAMMA = 0.99\n",
     "EPS_START = 0.9\n",
-    "EPS_END = 0.05\n",
-    "EPS_DECAY = 1000\n",
+    "EPS_END = 0.01\n",
+    "EPS_DECAY = 2500\n",
     "TAU = 0.005\n",
-    "LR = 1e-4\n",
+    "LR = 3e-4\n",
+    "\n",
     "\n",
     "# Get number of actions from gym action space\n",
     "n_actions = env.action_space.n\n",

_downloads/c28f42852d456daf9af72da6c6909556/captumyt.ipynb

@@ -37,7 +37,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "4d0c1f3c",
+   "id": "4d1f56b9",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -53,7 +53,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c2d4950b",
+   "id": "810109c0",
    "metadata": {},
    "source": [
     "\n",

_downloads/e2e556f6b4693c2cef716dd7f40caaf6/tensorboardyt_tutorial.ipynb

@@ -35,7 +35,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "36b705df",
+   "id": "6a2acd46",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "00ca459b",
+   "id": "effddd93",
    "metadata": {},
    "source": [
     "\n",

_downloads/ed9d4f94afb79f7dada6742a06c486a5/autogradyt_tutorial.ipynb

@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "4a5e0021",
+   "id": "7518f449",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5d13281e",
+   "id": "63efbf93",
    "metadata": {},
    "source": [
     "\n",

_downloads/fe726e041160526cf828806536922cf6/modelsyt_tutorial.ipynb

@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "460a80a0",
+   "id": "cd6cce52",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c45c6395",
+   "id": "678191f5",
    "metadata": {},
    "source": [
     "\n",