Update to make things work with new layout

src/primaite/config/_package_data/example_config.yaml

@@ -15,7 +15,8 @@ io_settings:
   checkpoint_interval: 5
 
 
-game_config:
+game:
+  max_episode_length: 256
   ports:
   - ARP
   - DNS

src/primaite/game/environment.py

@@ -1,11 +1,9 @@
-from typing import Any, Dict, List, Optional, SupportsFloat, Tuple, TYPE_CHECKING
+from typing import Any, Dict, List, Optional, SupportsFloat, Tuple
 
 import gymnasium
 from gymnasium.core import ActType, ObsType
 
 from primaite.game.agent.interface import ProxyAgent
-
-if TYPE_CHECKING:
 from primaite.game.game import PrimaiteGame
 
 
@@ -17,10 +15,10 @@ class PrimaiteGymEnv(gymnasium.Env):
     assumptions about the agent list always having a list of length 1.
     """
 
-    def __init__(self, session: "PrimaiteGame", agents: List[ProxyAgent]):
+    def __init__(self, game: PrimaiteGame, agents: List[ProxyAgent]):
         """Initialise the environment."""
         super().__init__()
-        self.session: "PrimaiteGame" = session
+        self.game: "PrimaiteGame" = game
         self.agent: ProxyAgent = agents[0]
 
     def step(self, action: ActType) -> Tuple[ObsType, SupportsFloat, bool, bool, Dict[str, Any]]:
@@ -28,24 +26,24 @@ class PrimaiteGymEnv(gymnasium.Env):
         # make ProxyAgent store the action chosen my the RL policy
         self.agent.store_action(action)
         # apply_agent_actions accesses the action we just stored
-        self.session.apply_agent_actions()
+        self.game.apply_agent_actions()
-        self.session.advance_timestep()
+        self.game.advance_timestep()
-        state = self.session.get_sim_state()
+        state = self.game.get_sim_state()
-        self.session.update_agents(state)
+        self.game.update_agents(state)
 
         next_obs = self._get_obs()
         reward = self.agent.reward_function.current_reward
         terminated = False
-        truncated = self.session.calculate_truncated()
+        truncated = self.game.calculate_truncated()
         info = {}
 
         return next_obs, reward, terminated, truncated, info
 
     def reset(self, seed: Optional[int] = None) -> Tuple[ObsType, Dict[str, Any]]:
         """Reset the environment."""
-        self.session.reset()
+        self.game.reset()
-        state = self.session.get_sim_state()
+        state = self.game.get_sim_state()
-        self.session.update_agents(state)
+        self.game.update_agents(state)
         next_obs = self._get_obs()
         info = {}
         return next_obs, info

src/primaite/game/game.py

@@ -177,7 +177,7 @@ class PrimaiteGame:
         :rtype: PrimaiteSession
         """
         game = cls()
-        game.options = PrimaiteGameOptions(cfg["game"])
+        game.options = PrimaiteGameOptions(**cfg["game"])
 
         # 1. create simulation
         sim = game.simulation
@@ -305,8 +305,7 @@ class PrimaiteGame:
             game.ref_map_links[link_cfg["ref"]] = new_link.uuid
 
         # 3. create agents
-        game_cfg = cfg["game_config"]
+        agents_cfg = cfg["agents"]
-        agents_cfg = game_cfg["agents"]
 
         for agent_cfg in agents_cfg:
             agent_ref = agent_cfg["ref"]  # noqa: F841

src/primaite/notebooks/train_rllib_single_agent.ipynb

@@ -4,19 +4,7 @@
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {},
-   "outputs": [
+   "outputs": [],
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/cade/repos/PrimAITE/venv/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n",
-      "2023-11-18 09:06:45,876\tINFO util.py:159 -- Missing packages: ['ipywidgets']. Run `pip install -U ipywidgets`, then restart the notebook server for rich notebook output.\n",
-      "2023-11-18 09:06:48,446\tINFO util.py:159 -- Missing packages: ['ipywidgets']. Run `pip install -U ipywidgets`, then restart the notebook server for rich notebook output.\n",
-      "2023-11-18 09:06:48,692\tWARNING __init__.py:10 -- PG has/have been moved to `rllib_contrib` and will no longer be maintained by the RLlib team. You can still use it/them normally inside RLlib util Ray 2.8, but from Ray 2.9 on, all `rllib_contrib` algorithms will no longer be part of the core repo, and will therefore have to be installed separately with pinned dependencies for e.g. ray[rllib] and other packages! See https://github.com/ray-project/ray/tree/master/rllib_contrib#rllib-contrib for more information on the RLlib contrib effort.\n"
-     ]
-    }
-   ],
    "source": [
     "from primaite.game.game import PrimaiteGame\n",
     "from primaite.game.environment import PrimaiteGymEnv\n",
@@ -56,7 +44,7 @@
     "with open(example_config_path(), 'r') as f:\n",
     "    cfg = yaml.safe_load(f)\n",
     "\n",
-    "sess = PrimaiteGame.from_config(cfg)"
+    "game = PrimaiteGame.from_config(cfg)"
    ]
   },
   {
@@ -65,44 +53,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sess.env = PrimaiteGymEnv(session=sess, agents=sess.rl_agents)"
+    "gym = PrimaiteGymEnv(game=game, agents=game.rl_agents)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "env = sess.env"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "<primaite.game.environment.PrimaiteGymEnv at 0x7fad7190d7b0>"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "env"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {