added report, add answer to 3rd question

Author: astelmashenko

Quadcopter_Project.ipynb

@@ -682,7 +682,10 @@
     "- Was there a gradual learning curve, or an aha moment?\n",
     "- How good was the final performance of the agent? (e.g. mean rewards over the last 10 episodes)\n",
     "\n",
-    "**Answer**:"
+    "**Answer**:\n",
+    "- it was task to just hover quadcopter, I consider this task as easy one, because it only wants on single point to achieve.,\n",
+    "- it was a gradual learing curve, however agent learned that falling down is the best way to maximize reward for an apisode.,\n",
+    "- final reward was 56, which tends to the best result over past episodes"
    ]
   },
   {