add actions to enable/disable ports in routers/firewalls, improve notebook for training PPO agents

src/primaite/notebooks/Training-an-SB3-Agent.ipynb

@@ -45,7 +45,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from stable_baselines3 import PPO"
+    "from stable_baselines3 import PPO\n",
+    "\n",
+    "EPISODE_LEN = 128\n",
+    "NO_STEPS = EPISODE_LEN * 10\n",
+    "BATCH_SIZE = EPISODE_LEN * 10\n",
+    "TOTAL_TIMESTEPS = 5e3 * EPISODE_LEN\n",
+    "LEARNING_RATE = 3e-4"
    ]
   },
   {
@@ -54,7 +60,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model = PPO('MlpPolicy', gym)\n"
+    "model = PPO('MlpPolicy', gym, learning_rate=LEARNING_RATE,  n_steps=NO_STEPS, batch_size=BATCH_SIZE, verbose=0, tensorboard_log=\"./PPO_UC2/\")\n"
    ]
   },
   {
@@ -63,7 +69,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model.learn(total_timesteps=10)\n"
+    "model.learn(total_timesteps=TOTAL_TIMESTEPS)\n"
    ]
   },
   {
@@ -72,7 +78,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model.save(\"deleteme\")"
+    "model.save(\"PrimAITE-v3.0.0b7-PPO\")"
    ]
   },
   {
@@ -80,7 +86,21 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "eval_model = PPO(\"MlpPolicy\", gym)\n",
+    "eval_model = PPO.load(\"PrimAITE-v3.0.0b7-PPO\", gym)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from stable_baselines3.common.evaluation import evaluate_policy\n",
+    "\n",
+    "evaluate_policy(eval_model, gym, n_eval_episodes=10)"
+   ]
   }
  ],
  "metadata": {
@@ -99,7 +119,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.9.18"
   }
  },
  "nbformat": 4,