File size: 11,755 Bytes
1ec1c03 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 |
{
"cells": [
{
"cell_type": "markdown",
"source": [
"### The environment 🎮\n",
"\n",
"- https://gymnasium.farama.org/environments/classic_control/mountain_car/\n",
"\n",
"### The library used 📚\n",
"\n",
"- [Stable-Baselines3](https://stable-baselines3.readthedocs.io/en/master/)"
],
"metadata": {
"id": "x7oR6R-ZIbeS"
}
},
{
"cell_type": "markdown",
"metadata": {
"id": "jeDAH0h0EBiG"
},
"source": [
"## Install dependencies and create a virtual screen 🔽\n"
]
},
{
"cell_type": "code",
"source": [
"!apt install swig cmake"
],
"metadata": {
"id": "yQIGLPDkGhgG"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "9XaULfDZDvrC"
},
"outputs": [],
"source": [
"!pip install -r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit1/requirements-unit1.txt"
]
},
{
"cell_type": "markdown",
"source": [
"During the notebook, we'll need to generate a replay video. To do so, with colab, **we need to have a virtual screen to be able to render the environment** (and thus record the frames).\n",
"\n",
"Hence the following cell will install virtual screen libraries and create and run a virtual screen 🖥"
],
"metadata": {
"id": "BEKeXQJsQCYm"
}
},
{
"cell_type": "code",
"source": [
"!sudo apt-get update\n",
"!sudo apt-get install -y python3-opengl\n",
"!apt install ffmpeg\n",
"!apt install xvfb\n",
"!pip3 install pyvirtualdisplay"
],
"metadata": {
"id": "j5f2cGkdP-mb"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"To make sure the new installed libraries are used, **sometimes it's required to restart the notebook runtime**. The next cell will force the **runtime to crash, so you'll need to connect again and run the code starting from here**. Thanks to this trick, **we will be able to run our virtual screen.**"
],
"metadata": {
"id": "TCwBTAwAW9JJ"
}
},
{
"cell_type": "code",
"source": [
"import os\n",
"os.kill(os.getpid(), 9)"
],
"metadata": {
"id": "cYvkbef7XEMi"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Virtual display\n",
"from pyvirtualdisplay import Display\n",
"\n",
"virtual_display = Display(visible=0, size=(1400, 900))\n",
"virtual_display.start()"
],
"metadata": {
"id": "BE5JWP5rQIKf"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "wrgpVFqyENVf"
},
"source": [
"## Import the packages 📦\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "cygWLPGsEQ0m"
},
"outputs": [],
"source": [
"import gymnasium\n",
"\n",
"from huggingface_sb3 import load_from_hub, package_to_hub\n",
"from huggingface_hub import notebook_login # To log to our Hugging Face account to be able to upload models to the Hub.\n",
"\n",
"from stable_baselines3 import PPO\n",
"from stable_baselines3.common.env_util import make_vec_env\n",
"from stable_baselines3.common.evaluation import evaluate_policy\n",
"from stable_baselines3.common.monitor import Monitor"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "w7vOFlpA_ONz"
},
"outputs": [],
"source": [
"import gymnasium as gym\n",
"\n",
"# First, we create our environment\n",
"env = gym.make(\"ALE/Tetris-v5\")\n",
"\n",
"# Then we reset this environment\n",
"observation, info = env.reset()\n",
"\n",
"for _ in range(20):\n",
" # Take a random action\n",
" action = env.action_space.sample()\n",
" print(\"Action taken:\", action)\n",
"\n",
" # Do this action in the environment and get\n",
" # next_state, reward, terminated, truncated and info\n",
" observation, reward, terminated, truncated, info = env.step(action)\n",
"\n",
" # If the game is terminated (in our case we land, crashed) or truncated (timeout)\n",
" if terminated or truncated:\n",
" # Reset the environment\n",
" print(\"Environment is reset\")\n",
" observation, info = env.reset()\n",
"\n",
"env.close()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "poLBgRocF9aT"
},
"source": [
"Let's see what the Environment looks like:\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ZNPG0g_UGCfh"
},
"outputs": [],
"source": [
"# We create our environment with gym.make(\"<name_of_the_environment>\")\n",
"env = gym.make(\"ALE/Tetris-v5\")\n",
"env.reset()\n",
"print(\"_____OBSERVATION SPACE_____ \\n\")\n",
"print(\"Observation Space Shape\", env.observation_space.shape)\n",
"print(\"Sample observation\", env.observation_space.sample()) # Get a random observation"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "We5WqOBGLoSm"
},
"outputs": [],
"source": [
"print(\"\\n _____ACTION SPACE_____ \\n\")\n",
"print(\"Action Space Shape\", env.action_space.n)\n",
"print(\"Action Space Sample\", env.action_space.sample()) # Take a random action"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "dFD9RAFjG8aq"
},
"source": [
"#### Vectorized Environment\n",
"\n",
"- We create a vectorized environment (a method for stacking multiple independent environments into a single environment) of 16 environments, this way, **we'll have more diverse experiences during the training.**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "99hqQ_etEy1N"
},
"outputs": [],
"source": [
"# Create the environment\n",
"env = make_vec_env('ALE/Tetris-v5', n_envs=16)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "QAN7B0_HCVZC"
},
"source": [
"#### Model and hyperparameters"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "543OHYDfcjK4"
},
"outputs": [],
"source": [
"model = PPO(\n",
" policy = 'MlpPolicy',\n",
" env = env,\n",
" n_steps = 1024,\n",
" batch_size = 64,\n",
" n_epochs = 4,\n",
" gamma = 0.99,\n",
" gae_lambda = 0.98,\n",
" ent_coef = 0.01,\n",
" verbose=1)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ClJJk88yoBUi"
},
"source": [
"## Train the PPO agent 🏃\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "poBCy9u_csyR"
},
"outputs": [],
"source": [
"model.learn(total_timesteps=100000)\n",
"# Save the model\n",
"model_name = \"Tetris-v5\"\n",
"model.save(model_name)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "BqPKw3jt_pG5"
},
"source": [
"#### Evaluate"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "zpz8kHlt_a_m"
},
"outputs": [],
"source": [
"#@title\n",
"eval_env = Monitor(gym.make(\"ALE/Tetris-v5\"))\n",
"mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)\n",
"print(f\"mean_reward={mean_reward:.2f} +/- {std_reward}\")"
]
},
{
"cell_type": "markdown",
"source": [
"#### Upload to hub"
],
"metadata": {
"id": "7YFBLHXDPuH5"
}
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "GZiFBBlzxzxY"
},
"outputs": [],
"source": [
"notebook_login()\n",
"!git config --global credential.helper store"
]
},
{
"cell_type": "code",
"source": [
"import gymnasium as gym\n",
"\n",
"from stable_baselines3 import PPO\n",
"from stable_baselines3.common.vec_env import DummyVecEnv\n",
"from stable_baselines3.common.env_util import make_vec_env\n",
"\n",
"from huggingface_sb3 import package_to_hub\n",
"\n",
"# PLACE the variables you've just defined two cells above\n",
"# Define the name of the environment\n",
"env_id = \"ALE/Tetris-v5\"\n",
"\n",
"# TODO: Define the model architecture we used\n",
"model_architecture = \"PPO\"\n",
"\n",
"## Define a repo_id\n",
"## repo_id is the id of the model repository from the Hugging Face Hub (repo_id = {organization}/{repo_name}\n",
"## CHANGE WITH YOUR REPO ID\n",
"repo_id = \"chirbard/ppo-Tetris-v5\" # Change with your repo id, you can't push with mine 😄\n",
"\n",
"## Define the commit message\n",
"commit_message = \"Upload PPO Tetris-v5 trained agent\"\n",
"\n",
"# Create the evaluation env and set the render_mode=\"rgb_array\"\n",
"eval_env = DummyVecEnv([lambda: gym.make(env_id, render_mode=\"rgb_array\")])\n",
"\n",
"# PLACE the package_to_hub function you've just filled here\n",
"package_to_hub(model=model, # Our trained model\n",
" model_name=model_name, # The name of our trained model\n",
" model_architecture=model_architecture, # The model architecture we used: in our case PPO\n",
" env_id=env_id, # Name of the environment\n",
" eval_env=eval_env, # Evaluation Environment\n",
" repo_id=repo_id, # id of the model repository from the Hugging Face Hub (repo_id = {organization}/{repo_name}\n",
" commit_message=commit_message)\n"
],
"metadata": {
"id": "I2E--IJu8JYq"
},
"execution_count": null,
"outputs": []
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"private_outputs": true,
"provenance": [],
"collapsed_sections": [
"QAN7B0_HCVZC",
"BqPKw3jt_pG5"
]
},
"gpuClass": "standard",
"kernelspec": {
"display_name": "Python 3.9.7",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"version": "3.9.7"
},
"vscode": {
"interpreter": {
"hash": "ed7f8024e43d3b8f5ca3c5e1a8151ab4d136b3ecee1e3fd59e0766ccc55e1b10"
}
}
},
"nbformat": 4,
"nbformat_minor": 0
} |