minor changes

dqn_wordle.ipynb

@@ -0,0 +1,114 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import gym\n",
+    "import gym_wordle\n",
+    "from stable_baselines3 import DQN\n",
+    "import numpy as np\n",
+    "import tqdm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "env = gym.make(\"Wordle-v0\")\n",
+    "\n",
+    "print(env)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "total_timesteps = 100000\n",
+    "model = DQN(\"MlpPolicy\", env, verbose=0)\n",
+    "model.learn(total_timesteps=total_timesteps, progress_bar=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def test(model):\n",
+    "\n",
+    "    end_rewards = []\n",
+    "\n",
+    "    for i in range(1000):\n",
+    "        \n",
+    "        state = env.reset()\n",
+    "\n",
+    "        done = False\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",
+    "        end_rewards.append(reward == 0)\n",
+    "        \n",
+    "    return np.sum(end_rewards) / len(end_rewards)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.save(\"dqn_wordle\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = DQN.load(\"dqn_wordle\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(test(model))"
+   ]
+  }
+ ],
+ "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
+}

dqn_wordle.py

@@ -1,24 +0,0 @@
-import gym
-import gym_wordle
-from stable_baselines3 import DQN
-
-env = gym.make("Wordle-v0")
-done = False
-
-print(env)
-
-model = DQN("MlpPolicy", env, verbose=1)
-model.learn(total_timesteps=10000, log_interval=100)
-model.save("dqn_wordle")
-
-del model # remove to demonstrate saving and loading
-
-model = DQN.load("dqn_wordle")
-
-state = env.reset()
-
-while not done:
-
-    action, _states = model.predict(state, deterministic=True)
-
-    state, reward, done, info = env.step(action)