backport 3.2 changes to core

src/primaite/notebooks/Action-masking.ipynb

@@ -101,7 +101,6 @@
     "from primaite.session.ray_envs import PrimaiteRayEnv\n",
     "from ray.rllib.algorithms.ppo import PPOConfig\n",
     "import yaml\n",
-    "from ray import air, tune\n",
     "from ray.rllib.examples.rl_modules.classes.action_masking_rlm import ActionMaskingTorchRLModule\n",
     "from ray.rllib.core.rl_module.rl_module import SingleAgentRLModuleSpec\n"
    ]
@@ -135,8 +134,7 @@
     "    .training(train_batch_size=128)\n",
     ")\n",
     "algo = config.build()\n",
-    "for i in range(2):\n",
-    "    results = algo.train()"
+    "results = algo.train()"
    ]
   },
   {
@@ -191,8 +189,7 @@
     "    .training(train_batch_size=128)\n",
     ")\n",
     "algo = config.build()\n",
-    "for i in range(2):\n",
-    "    results = algo.train()"
+    "results = algo.train()"
    ]
   }
  ],
@@ -212,7 +209,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.8"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

src/primaite/notebooks/Training-an-RLLIB-MARL-System.ipynb

@@ -24,14 +24,11 @@
    "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",
@@ -72,7 +69,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Set training parameters and start the training\n",
+    "#### Start the training\n",
     "This example will save outputs to a default Ray directory and use mostly default settings."
    ]
   },
@@ -82,13 +79,8 @@
    "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()"
+    "algo = config.build()\n",
+    "results = algo.train()"
    ]
   }
  ],

src/primaite/notebooks/Training-an-RLLib-Agent.ipynb

@@ -17,12 +17,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from primaite.game.game import PrimaiteGame\n",
     "import yaml\n",
     "from primaite.config.load import data_manipulation_config_path\n",
     "\n",
     "from primaite.session.ray_envs import PrimaiteRayEnv\n",
-    "from ray import air, tune\n",
     "import ray\n",
     "from ray.rllib.algorithms.ppo import PPOConfig\n",
     "\n",
@@ -64,7 +62,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Set training parameters and start the training"
+    "#### Start the training"
    ]
   },
   {
@@ -73,13 +71,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "tune.Tuner(\n",
-    "    \"PPO\",\n",
-    "    run_config=air.RunConfig(\n",
-    "        stop={\"timesteps_total\": 512}\n",
-    "    ),\n",
-    "    param_space=config\n",
-    ").fit()\n"
+    "algo = config.build()\n",
+    "results = algo.train()\n"
    ]
   }
  ],