feat(training): implement LanderCliEnv wrapping the GameCli subprocess
This commit is contained in:
134
Training/lander_cli_env.py
Normal file
134
Training/lander_cli_env.py
Normal file
@@ -0,0 +1,134 @@
|
||||
"""Gymnasium environment that wraps the GameCli C# binary as a subprocess.
|
||||
|
||||
Speaks the line-delimited JSON protocol defined in:
|
||||
docs/superpowers/specs/2026-07-17-cursor-following-lander-design.md
|
||||
|
||||
Each episode picks a random target in [0,1]^2 at reset time and holds it fixed.
|
||||
Never terminates — episodes end via truncation at max_episode_steps.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
from typing import Any, Optional
|
||||
|
||||
import gymnasium as gym
|
||||
import numpy as np
|
||||
from gymnasium import spaces
|
||||
|
||||
|
||||
class LanderCliEnv(gym.Env):
|
||||
"""One CLI subprocess per env instance. Not thread-safe; safe under SubprocVecEnv."""
|
||||
|
||||
metadata = {"render_modes": []}
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
cli_binary: str,
|
||||
max_episode_steps: int = 1000,
|
||||
) -> None:
|
||||
super().__init__()
|
||||
self._cli_binary = cli_binary
|
||||
self._max_episode_steps = max_episode_steps
|
||||
|
||||
self._proc: Optional[subprocess.Popen] = None
|
||||
self._target: tuple[float, float] = (0.5, 0.5)
|
||||
self._step_count: int = 0
|
||||
|
||||
self._start_process()
|
||||
self._read_init()
|
||||
|
||||
self.observation_space = spaces.Box(
|
||||
low=-np.inf, high=np.inf, shape=(7,), dtype=np.float32
|
||||
)
|
||||
self.action_space = spaces.Discrete(4)
|
||||
|
||||
# -------- subprocess lifecycle --------
|
||||
|
||||
def _start_process(self) -> None:
|
||||
self._proc = subprocess.Popen(
|
||||
[self._cli_binary],
|
||||
stdin=subprocess.PIPE,
|
||||
stdout=subprocess.PIPE,
|
||||
stderr=subprocess.PIPE,
|
||||
text=True,
|
||||
bufsize=1, # line-buffered
|
||||
)
|
||||
|
||||
def _read_init(self) -> None:
|
||||
assert self._proc is not None and self._proc.stdout is not None
|
||||
line = self._proc.stdout.readline()
|
||||
if not line:
|
||||
raise RuntimeError("CLI died before emitting init handshake")
|
||||
msg = json.loads(line)
|
||||
if "init" not in msg:
|
||||
raise RuntimeError(f"expected init handshake, got: {line!r}")
|
||||
|
||||
def _send(self, obj: dict[str, Any]) -> None:
|
||||
assert self._proc is not None and self._proc.stdin is not None
|
||||
self._proc.stdin.write(json.dumps(obj) + "\n")
|
||||
self._proc.stdin.flush()
|
||||
|
||||
def _recv(self) -> dict[str, Any]:
|
||||
assert self._proc is not None and self._proc.stdout is not None
|
||||
line = self._proc.stdout.readline()
|
||||
if not line:
|
||||
raise RuntimeError("CLI closed stdout unexpectedly")
|
||||
return json.loads(line)
|
||||
|
||||
# -------- gym.Env API --------
|
||||
|
||||
def reset(
|
||||
self, *, seed: Optional[int] = None, options: Optional[dict] = None
|
||||
) -> tuple[np.ndarray, dict]:
|
||||
super().reset(seed=seed)
|
||||
# Sample a fresh target each episode; the Gymnasium-provided
|
||||
# np_random is deterministic given `seed`.
|
||||
tx = float(self.np_random.uniform(0.05, 0.95))
|
||||
ty = float(self.np_random.uniform(0.05, 0.95))
|
||||
self._target = (tx, ty)
|
||||
self._step_count = 0
|
||||
|
||||
cmd: dict[str, Any] = {"cmd": "reset"}
|
||||
if seed is not None:
|
||||
cmd["seed"] = int(seed)
|
||||
self._send(cmd)
|
||||
msg = self._recv()
|
||||
obs = np.asarray(msg["obs"], dtype=np.float32)
|
||||
# Overwrite the CLI's dummy (0.5, 0.5) target displacement with the real one.
|
||||
# dx = target.X - ship.X, dy = target.Y - ship.Y.
|
||||
obs[0] = tx - msg["state"]["x"]
|
||||
obs[1] = ty - msg["state"]["y"]
|
||||
return obs, {}
|
||||
|
||||
def step(self, action: int) -> tuple[np.ndarray, float, bool, bool, dict]:
|
||||
self._send({"action": int(action), "target": list(self._target)})
|
||||
msg = self._recv()
|
||||
obs = np.asarray(msg["obs"], dtype=np.float32)
|
||||
reward = float(msg["reward"])
|
||||
self._step_count += 1
|
||||
truncated = self._step_count >= self._max_episode_steps
|
||||
terminated = False # continuous hover task
|
||||
return obs, reward, terminated, truncated, {}
|
||||
|
||||
def close(self) -> None:
|
||||
if self._proc is None:
|
||||
return
|
||||
try:
|
||||
if self._proc.stdin is not None:
|
||||
self._proc.stdin.close()
|
||||
except (BrokenPipeError, OSError):
|
||||
pass
|
||||
try:
|
||||
self._proc.wait(timeout=3)
|
||||
except subprocess.TimeoutExpired:
|
||||
self._proc.kill()
|
||||
self._proc.wait(timeout=1)
|
||||
self._proc = None
|
||||
|
||||
def __del__(self) -> None:
|
||||
try:
|
||||
self.close()
|
||||
except Exception:
|
||||
pass
|
||||
Reference in New Issue
Block a user