{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [],
   "source": [
    "import gym\n",
    "import gym_wordle\n",
    "from stable_baselines3 import DQN, PPO, common\n",
    "import numpy as np\n",
    "import tqdm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<Monitor<WordleEnv instance>>\n"
     ]
    }
   ],
   "source": [
    "env = gym_wordle.wordle.WordleEnv()\n",
    "env = common.monitor.Monitor(env)\n",
    "\n",
    "print(env)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Using cuda device\n",
      "Wrapping the env in a DummyVecEnv.\n"
     ]
    }
   ],
   "source": [
    "total_timesteps = 1000\n",
    "model = PPO(\"MlpPolicy\", env, verbose=1)\n",
    "model.learn(total_timesteps=total_timesteps)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.save(\"dqn_wordle\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = PPO.load(\"dqn_wordle\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[16 18  5 15 14  3  3  1  3  3]\n",
      " [ 0  0  0  0  0  0  0  0  0  0]\n",
      " [ 0  0  0  0  0  0  0  0  0  0]\n",
      " [ 0  0  0  0  0  0  0  0  0  0]\n",
      " [ 0  0  0  0  0  0  0  0  0  0]\n",
      " [ 0  0  0  0  0  0  0  0  0  0]] -1.0 False {}\n",
      "[[16 18  5 15 14  3  3  1  3  3]\n",
      " [16 18  5 15 14  3  3  1  3  3]\n",
      " [ 0  0  0  0  0  0  0  0  0  0]\n",
      " [ 0  0  0  0  0  0  0  0  0  0]\n",
      " [ 0  0  0  0  0  0  0  0  0  0]\n",
      " [ 0  0  0  0  0  0  0  0  0  0]] -1.0 False {}\n",
      "[[16 18  5 15 14  3  3  1  3  3]\n",
      " [16 18  5 15 14  3  3  1  3  3]\n",
      " [16 18  5 15 14  3  3  1  3  3]\n",
      " [ 0  0  0  0  0  0  0  0  0  0]\n",
      " [ 0  0  0  0  0  0  0  0  0  0]\n",
      " [ 0  0  0  0  0  0  0  0  0  0]] -1.0 False {}\n",
      "[[16 18  5 15 14  3  3  1  3  3]\n",
      " [16 18  5 15 14  3  3  1  3  3]\n",
      " [16 18  5 15 14  3  3  1  3  3]\n",
      " [16 18  5 15 14  3  3  1  3  3]\n",
      " [ 0  0  0  0  0  0  0  0  0  0]\n",
      " [ 0  0  0  0  0  0  0  0  0  0]] -1.0 False {}\n",
      "[[16 18  5 15 14  3  3  1  3  3]\n",
      " [16 18  5 15 14  3  3  1  3  3]\n",
      " [16 18  5 15 14  3  3  1  3  3]\n",
      " [16 18  5 15 14  3  3  1  3  3]\n",
      " [16 18  5 15 14  3  3  1  3  3]\n",
      " [ 0  0  0  0  0  0  0  0  0  0]] -1.0 False {}\n",
      "[[16 18  5 15 14  3  3  1  3  3]\n",
      " [16 18  5 15 14  3  3  1  3  3]\n",
      " [16 18  5 15 14  3  3  1  3  3]\n",
      " [16 18  5 15 14  3  3  1  3  3]\n",
      " [16 18  5 15 14  3  3  1  3  3]\n",
      " [16 18  5 15 14  3  3  1  3  3]] -1.0 True {}\n"
     ]
    },
    {
     "ename": "KeyError",
     "evalue": "'correct'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[82], line 19\u001b[0m\n\u001b[1;32m     15\u001b[0m         state, reward, done, info \u001b[38;5;241m=\u001b[39m env\u001b[38;5;241m.\u001b[39mstep(action)\n\u001b[1;32m     17\u001b[0m         \u001b[38;5;28mprint\u001b[39m(state, reward, done, info)\n\u001b[0;32m---> 19\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[43minfo\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcorrect\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m:\n\u001b[1;32m     20\u001b[0m         wins \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[1;32m     22\u001b[0m     \u001b[38;5;66;03m#end_rewards.append(reward == 0)\u001b[39;00m\n\u001b[1;32m     23\u001b[0m     \n\u001b[1;32m     24\u001b[0m \u001b[38;5;66;03m#return np.sum(end_rewards) / len(end_rewards)\u001b[39;00m\n",
      "\u001b[0;31mKeyError\u001b[0m: 'correct'"
     ]
    }
   ],
   "source": [
    "env = gym_wordle.wordle.WordleEnv()\n",
    "\n",
    "for i in range(1):\n",
    "        \n",
    "    state = env.reset()\n",
    "\n",
    "    done = False\n",
    "\n",
    "    wins = 0\n",
    "\n",
    "    while not done:\n",
    "\n",
    "        action, _states = model.predict(state, deterministic=True)\n",
    "\n",
    "        state, reward, done, info = env.step(action)\n",
    "\n",
    "        print(state, reward, done, info)\n",
    "\n",
    "    if info[\"correct\"]:\n",
    "        wins += 1\n",
    "        \n",
    "    #end_rewards.append(reward == 0)\n",
    "    \n",
    "#return np.sum(end_rewards) / len(end_rewards)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}