feat(*): Add self-play RL training pipeline with PPO trainer, in-game GDScript policy inference, and bot opponent support in Match mode

training/cosmic_env.py

@@ -0,0 +1,76 @@
+"""Godot RL Agents environment wrappers that run Cosmic Clash from source.
+
+Stock GodotEnv expects an *exported* game executable and rewrites its path
+per-platform. These subclasses launch the project straight from the repo with
+a Godot binary instead (no export step), pointing it at the training scene.
+Each Godot instance contributes two agents (one ship per team) that share the
+learning policy: self-play by construction.
+"""
+
+import pathlib
+import subprocess
+
+from godot_rl.core.godot_env import GodotEnv
+from godot_rl.wrappers.stable_baselines_wrapper import StableBaselinesGodotEnv
+
+REPO_ROOT = pathlib.Path(__file__).resolve().parent.parent
+GAME_DIR = REPO_ROOT / "Game"
+TRAINING_SCENE = "res://scenes/training.tscn"
+
+
+class CosmicClashEnv(GodotEnv):
+    """GodotEnv that launches `godot --path Game res://scenes/training.tscn`."""
+
+    # env_path is a Godot binary, not an exported game: skip the suffix and
+    # platform checks stock GodotEnv applies to exported executables.
+    def _set_platform_suffix(self, env_path: str) -> str:
+        return env_path
+
+    def check_platform(self, filename: str):
+        pass
+
+    def _launch_env(self, env_path, port, show_window, framerate, seed, action_repeat, speedup, **kwargs):
+        # sync.gd reads --key=value pairs from the raw command line; they must
+        # NOT go after a `--` separator or OS.get_cmdline_args() drops them.
+        cmd = [
+            env_path,
+            "--path",
+            str(GAME_DIR),
+            TRAINING_SCENE,
+            f"--port={port}",
+            f"--env_seed={seed}",
+        ]
+        if not show_window:
+            cmd += ["--headless", "--disable-render-loop"]
+        if framerate is not None:
+            cmd += ["--fixed-fps", str(framerate)]
+        if action_repeat is not None:
+            cmd.append(f"--action_repeat={action_repeat}")
+        if speedup is not None:
+            cmd.append(f"--speedup={speedup}")
+        for key, value in kwargs.items():
+            cmd.append(f"--{key}={value}")
+        self.proc = subprocess.Popen(cmd, start_new_session=True)
+
+
+class CosmicClashVecEnv(StableBaselinesGodotEnv):
+    """SB3 VecEnv over N parallel CosmicClashEnv instances.
+
+    convert_action_space=True flattens the env's (Box(6), Discrete(2)) action
+    space into a single Box(7): thrust xyz, rotation xyz, turbo (>0 means on).
+    """
+
+    def __init__(self, godot_bin: str, n_parallel: int = 1, seed: int = 0, port: int = GodotEnv.DEFAULT_PORT, **kwargs):
+        self.envs = [
+            CosmicClashEnv(
+                env_path=godot_bin,
+                convert_action_space=True,
+                port=port + p,
+                seed=seed + p,
+                **kwargs,
+            )
+            for p in range(n_parallel)
+        ]
+        self.n_parallel = n_parallel
+        self._check_valid_action_space()
+        self.results = None