更新PPO，增加PER DQN

projects/notebooks/Q-learning/Q-learning探索策略研究.ipynb

@@ -0,0 +1,32 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Q learning with different exploration strategies\n",
+    "\n",
+    "Authors: [johnjim0816](https://github.com/johnjim0816)\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.7.13 ('easyrl')",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.7.13"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "8994a120d39b6e6a2ecc94b4007f5314b68aa69fc88a7f00edf21be39b41f49c"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}