PrimAITE/src/primaite/notebooks/Training-an-SB3-Agent.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from primaite.game.game import PrimaiteGame\n",
    "from primaite.session.environment import PrimaiteGymEnv\n",
    "import yaml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from primaite.config.load import data_manipulation_config_path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(data_manipulation_config_path(), 'r') as f:\n",
    "    cfg = yaml.safe_load(f)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "gym = PrimaiteGymEnv(game_config=cfg)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from stable_baselines3 import PPO\n",
    "\n",
    "EPISODE_LEN = 128\n",
    "NO_STEPS = EPISODE_LEN * 10\n",
    "BATCH_SIZE = EPISODE_LEN * 10\n",
    "TOTAL_TIMESTEPS = 5e3 * EPISODE_LEN\n",
    "LEARNING_RATE = 3e-4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = PPO('MlpPolicy', gym, learning_rate=LEARNING_RATE,  n_steps=NO_STEPS, batch_size=BATCH_SIZE, verbose=0, tensorboard_log=\"./PPO_UC2/\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.learn(total_timesteps=TOTAL_TIMESTEPS)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.save(\"PrimAITE-v3.0.0b7-PPO\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "eval_model = PPO(\"MlpPolicy\", gym)\n",
    "eval_model = PPO.load(\"PrimAITE-v3.0.0b7-PPO\", gym)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from stable_baselines3.common.evaluation import evaluate_policy\n",
    "\n",
    "evaluate_policy(eval_model, gym, n_eval_episodes=10)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "venv",
   "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": "3.9.18"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}