{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Train a Multi agent system using RLLIB\n",
    "\n",
    "© Crown-owned copyright 2024, Defence Science and Technology Laboratory UK\n",
    "\n",
    "This notebook will demonstrate how to use the `PrimaiteRayMARLEnv` to train a very basic system with two PPO agents."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### First, Import packages and read our config file."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from primaite.game.game import PrimaiteGame\n",
    "import yaml\n",
    "\n",
    "from primaite.session.ray_envs import PrimaiteRayEnv\n",
    "from primaite import PRIMAITE_PATHS\n",
    "\n",
    "import ray\n",
    "from ray import air, tune\n",
    "from ray.rllib.algorithms.ppo import PPOConfig\n",
    "from primaite.session.ray_envs import PrimaiteRayMARLEnv\n",
    "\n",
    "# If you get an error saying this config file doesn't exist, you may need to run `primaite setup` in your command line\n",
    "# to copy the files to your user data path.\n",
    "with open(PRIMAITE_PATHS.user_config_path / 'example_config/data_manipulation_marl.yaml', 'r') as f:\n",
    "    cfg = yaml.safe_load(f)\n",
    "\n",
    "ray.init(local_mode=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Create a Ray algorithm config which accepts our two agents"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "config = (\n",
    "    PPOConfig()\n",
    "    .multi_agent(\n",
    "        policies={'defender_1','defender_2'}, # These names are the same as the agents defined in the example config.\n",
    "        policy_mapping_fn=lambda agent_id, episode, worker, **kw: agent_id,\n",
    "        )\n",
    "    .environment(env=PrimaiteRayMARLEnv, env_config=cfg)\n",
    "    .env_runners(num_env_runners=0)\n",
    "    .training(train_batch_size=128)\n",
    "    )\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Set training parameters and start the training\n",
    "This example will save outputs to a default Ray directory and use mostly default settings."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "tune.Tuner(\n",
    "    \"PPO\",\n",
    "    run_config=air.RunConfig(\n",
    "        stop={\"timesteps_total\": 5 * 128},\n",
    "    ),\n",
    "    param_space=config\n",
    ").fit()"
   ]
  }
 ],
 "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}