Fix multi agent system

src/primaite/notebooks/training_example_ray_multi_agent.ipynb

@@ -0,0 +1,127 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from primaite.game.game import PrimaiteGame\n",
+    "import yaml\n",
+    "from primaite.config.load import example_config_path\n",
+    "\n",
+    "from primaite.game.environment import PrimaiteRayEnv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(example_config_path(), 'r') as f:\n",
+    "    cfg = yaml.safe_load(f)\n",
+    "\n",
+    "game = PrimaiteGame.from_config(cfg)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# gym = PrimaiteRayEnv({\"game\":game})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import ray\n",
+    "from ray import air, tune\n",
+    "from ray.rllib.algorithms.ppo import PPOConfig"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ray.shutdown()\n",
+    "ray.init()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from primaite.game.environment import PrimaiteRayMARLEnv\n",
+    "\n",
+    "\n",
+    "env_config = {\"game\":game}\n",
+    "config = (\n",
+    "    PPOConfig()\n",
+    "    .environment(env=PrimaiteRayMARLEnv, env_config={\"game\":game})\n",
+    "    .rollouts(num_rollout_workers=0)\n",
+    "    .multi_agent(\n",
+    "        policies={agent.agent_name for agent in game.rl_agents},\n",
+    "        policy_mapping_fn=lambda agent_id, episode, worker, **kw: agent_id,\n",
+    "        )\n",
+    "    .training(train_batch_size=128)\n",
+    "    )\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tune.Tuner(\n",
+    "    \"PPO\",\n",
+    "    run_config=air.RunConfig(\n",
+    "        stop={\"training_iteration\": 128},\n",
+    "        checkpoint_config=air.CheckpointConfig(\n",
+    "            checkpoint_frequency=10,\n",
+    "        ),\n",
+    "    ),\n",
+    "    param_space=config\n",
+    ").fit()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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
+}