revert: 移除全部机器学习代码，回退到无 ML 版本

删除 RL/HRL/训练前端及其文档、脚本、测试与依赖：
- src/mcm26b/{rl,hrl,training_ui}/、planner/{rl,hrl}_loop.py、process_control.py
- project/（PPO 策略、训练、环境、评估）
- scripts/{train_rl,train_hrl_*,benchmark_rl,benchmark_hrl,pretrain_*_expert 等}
- tests/{test_rl*,test_hrl*,test_training_ui*}、tests/js/training_ui_harness.cjs
- docs/{algo-rl,hrl-*,training-ui*} 与相关计划条目、论文 PDF 回退

CLI 恢复为 grid/seven/bayes + directional，移除 --strategy rl|hrl、
--q4-strategy、--rl-model、--hrl-* 等参数；pyproject 删除 rl 依赖组与
PyTorch CUDA index，uv.lock 同步重生成。

保留此后的非 ML 改动（referee 回放、Q1/Q3 脚本、代码清理等）。
验证：pytest 232 passed；Q3/Q4 --self-test 全清通过。

project/README.md

@@ -1,29 +0,0 @@
-# project/ 薄兼容层
-
-题目 Prompt 要求 `project/` 目录树；本仓库的真实算法保持唯一一份，
-位于 `src/mcm26b`、`scripts/`。本目录只做 re-export/转发，不复制实现。
-
-| Prompt 路径 | 真实实现 |
-|---|---|
-| `env/simulator_client.py` | `src/mcm26b/protocol/client.py` |
-| `env/local_env.py` | `src/mcm26b/hrl/hierarchical_env.py`, `low_level_env.py` |
-| `env/particle_filter.py` | `src/mcm26b/particles.py` |
-| `policies/high_level_ppo.py` | `src/mcm26b/hrl/policy.py` |
-| `policies/low_level_ppo.py` | `src/mcm26b/hrl/policy.py`, `low_level_env.py` |
-| `train/curriculum.py` | `src/mcm26b/hrl/curriculum.py` |
-| `train/domain_randomization.py` | `src/mcm26b/hrl/curriculum.py` + 配置包装 |
-| `eval/evaluate.py` | `scripts/benchmark_hrl.py` |
-| `eval/ablation.py` | `scripts/ablate_hrl.py`（P2） |
-| `baselines/heuristic.py` | `src/mcm26b/planner/hrl_loop.py` 启发式降级 |
-| `baselines/end_to_end_ppo.py` | 显式未实现；单源局部 PPO 不冒充 E2E |
-
-使用示例：
-
-```python
-from project.env.local_env import make_local_env
-env = make_local_env(problem=3, stage=1, seed=7)
-obs, info = env.reset(seed=7)
-```
-
-P1 当前交付：`benchmark_hrl.py`、`train_hrl_high.py`、CLI `--strategy hrl`、
-`--q4-strategy hrl`。P2 的 BC/Optuna/消融在 smoke 通过后另开。

project/__init__.py

@@ -1,4 +0,0 @@
-"""题目 Prompt 所需目录树的薄兼容层。
-
-真实实现仍位于 ``src/mcm26b``；本包只做 re-export / CLI 转发，避免两份算法逻辑。
-"""

project/baselines/__init__.py

@@ -1,3 +0,0 @@
-from .heuristic import HeuristicHRL, run_heuristic
-
-__all__ = ["HeuristicHRL", "run_heuristic"]

project/baselines/end_to_end_ppo.py

@@ -1,16 +0,0 @@
-"""端到端 PPO 基线占位。
-
-按本轮确认：当前只交付局部 PPO 基线；raw-observation/raw-action 的真正
-端到端 PPO 不在 P0+P1 范围内，因此显式标记未实现，避免把单源局部选点
-PPO 误称为端到端 baseline。
-"""
-from __future__ import annotations
-
-
-def train_end_to_end_ppo(*args, **kwargs):
-    raise NotImplementedError(
-        "本轮只交付局部 PPO 基线；真正的端到端 PPO 基线标记为未实现，"
-        "需单独立项定义原始观测、动作与安全执行边界。")
-
-
-__all__ = ["train_end_to_end_ppo"]

project/baselines/heuristic.py

@@ -1,16 +0,0 @@
-"""兼容入口：信息增益/TSP/覆盖规则 + 高层启发式调度。"""
-from mcm26b.planner.bayes_loop import BayesLoop
-from mcm26b.planner.hrl_loop import HRLLoop
-
-
-def HeuristicHRL(*args, **kwargs):  # pylint: disable=invalid-name  # 兼容入口保留题面公开名
-    """返回无模型的高层 HRL 闭环（heuristic_action 降级路径）。"""
-    kwargs.setdefault("high_policy", None)
-    return HRLLoop(*args, **kwargs)
-
-
-def run_heuristic(*args, **kwargs):
-    return HeuristicHRL(*args, **kwargs).run()
-
-
-__all__ = ["HeuristicHRL", "run_heuristic", "BayesLoop", "HRLLoop"]

project/env/__init__.py

@@ -1,6 +0,0 @@
-from .simulator_client import SimulatorClient
-from .local_env import HierarchicalEnv, LowLevelEnv, HRLReward, make_local_env
-from .particle_filter import ChannelParticles
-
-__all__ = ["SimulatorClient", "HierarchicalEnv", "LowLevelEnv", "HRLReward",
-           "make_local_env", "ChannelParticles"]

project/env/local_env.py

@@ -1,22 +0,0 @@
-"""兼容入口：本地简化训练环境。
-
-HierarchicalEnv 是高层宏动作环境；LowLevelEnv 是独立八方向导航环境。
-本文件不复制实现，只转发 mcm26b.hrl 下的真实类。
-"""
-from mcm26b.hrl.hierarchical_env import HRLReward, HierarchicalEnv
-from mcm26b.hrl.low_level_env import LowLevelEnv
-
-__all__ = ["HierarchicalEnv", "LowLevelEnv", "HRLReward", "make_local_env"]
-
-
-def make_local_env(*, problem: int = 3, stage: int = 4, seed: int | None = None,
-                   fidelity: str = "production"):
-    """按题目 Prompt 的四阶段编号创建训练环境。"""
-    from mcm26b.hrl.curriculum import STAGES
-    if not 1 <= int(stage) <= len(STAGES):
-        raise ValueError(f"stage 必须在 1..{len(STAGES)}")
-    env = HierarchicalEnv(problem=problem, stage=STAGES[int(stage) - 1],
-                          fidelity=fidelity)
-    if seed is not None:
-        env.reset(seed=seed)
-    return env

project/env/particle_filter.py

@@ -1,4 +0,0 @@
-"""兼容入口：逐频道网格粒子/幸存集。"""
-from mcm26b.particles import ChannelParticles, angular_gap
-
-__all__ = ["ChannelParticles", "angular_gap"]

project/env/simulator_client.py

@@ -1,8 +0,0 @@
-"""兼容入口：真实类见 mcm26b.protocol.client。"""
-from mcm26b.protocol.client import (ActionRejected, ClearOutcome, DeadlineExceeded,
-                                    ExitInfo, MeasureOutcome, ProtocolError,
-                                    ProtocolViolation, SimulatorClient)
-
-__all__ = ["SimulatorClient", "MeasureOutcome", "ClearOutcome", "ExitInfo",
-           "ProtocolError", "ActionRejected", "ProtocolViolation",
-           "DeadlineExceeded"]

project/eval/__init__.py

@@ -1,4 +0,0 @@
-from .evaluate import run_benchmark
-from .ablation import run_ablation
-
-__all__ = ["run_benchmark", "run_ablation"]

project/eval/ablation.py

@@ -1,20 +0,0 @@
-"""兼容入口：调用 scripts/ablate_hrl.py（P2 后启用）。"""
-from __future__ import annotations
-
-import importlib.util
-from pathlib import Path
-
-
-def run_ablation(argv=None) -> int:
-    path = Path(__file__).resolve().parents[2] / "scripts" / "ablate_hrl.py"
-    if not path.exists():
-        raise NotImplementedError(
-            "scripts/ablate_hrl.py 尚未实现；P1 阶段只保证 benchmark/training/CLI。")
-    spec = importlib.util.spec_from_file_location("ablate_hrl_compat", path)
-    module = importlib.util.module_from_spec(spec)
-    assert spec.loader is not None
-    spec.loader.exec_module(module)
-    return int(module.main(argv))
-
-
-__all__ = ["run_ablation"]

project/eval/evaluate.py

@@ -1,17 +0,0 @@
-"""兼容入口：调用 scripts/benchmark_hrl.py。"""
-from __future__ import annotations
-
-import importlib.util
-from pathlib import Path
-
-
-def run_benchmark(argv=None) -> int:
-    path = Path(__file__).resolve().parents[2] / "scripts" / "benchmark_hrl.py"
-    spec = importlib.util.spec_from_file_location("benchmark_hrl_compat", path)
-    module = importlib.util.module_from_spec(spec)
-    assert spec.loader is not None
-    spec.loader.exec_module(module)
-    return int(module.main(argv))
-
-
-__all__ = ["run_benchmark"]

project/policies/__init__.py

@@ -1,5 +0,0 @@
-from .high_level_ppo import HighLevelPolicy, load_high_policy
-from .low_level_ppo import LowLevelPolicy, load_low_policy
-
-__all__ = ["HighLevelPolicy", "load_high_policy",
-           "LowLevelPolicy", "load_low_policy"]

project/policies/high_level_ppo.py

@@ -1,10 +0,0 @@
-"""兼容入口：高层 MaskablePPO 推理策略。"""
-from mcm26b.hrl.policy import HighLevelPolicy
-
-
-def load_high_policy(model_path: str, *, device: str = "auto",
-                     problem: int | None = None) -> HighLevelPolicy:
-    return HighLevelPolicy(model_path, device=device, problem=problem)
-
-
-__all__ = ["HighLevelPolicy", "load_high_policy"]

project/policies/low_level_ppo.py

@@ -1,9 +0,0 @@
-"""兼容入口：低层八方向到达策略（离线导航实验）。"""
-from mcm26b.hrl.policy import LowLevelPolicy
-
-
-def load_low_policy(model_path: str, *, device: str = "auto") -> LowLevelPolicy:
-    return LowLevelPolicy(model_path, device=device)
-
-
-__all__ = ["LowLevelPolicy", "load_low_policy"]

project/train/__init__.py

@@ -1,5 +0,0 @@
-from .curriculum import STAGES, Stage, make_scene, training_config
-from .domain_randomization import randomize_problem_config
-
-__all__ = ["STAGES", "Stage", "make_scene", "training_config",
-           "randomize_problem_config"]

project/train/curriculum.py

@@ -1,6 +0,0 @@
-"""兼容入口：课程学习与域随机化。"""
-from mcm26b.hrl.curriculum import (STAGES, Stage, make_scene, stage_with_noise,
-                                   training_config, training_spec)
-
-__all__ = ["STAGES", "Stage", "make_scene", "stage_with_noise",
-           "training_config", "training_spec"]

project/train/domain_randomization.py

@@ -1,31 +0,0 @@
-"""兼容入口：本地域随机化参数包装。
-
-当前真实随机化在 mcm26b.hrl.curriculum.make_scene 内完成；这里只暴露
-ProblemConfig 的显式替换助手，便于 Optuna/消融在实验配置中记录随机化范围。
-"""
-from __future__ import annotations
-
-import dataclasses
-from random import Random
-
-from mcm26b.config import ProblemConfig
-
-
-def randomize_problem_config(base: ProblemConfig, *, seed: int,
-                             bearing_error_half_deg: float | None = None,
-                             r_eff_range: tuple[float, float] | None = None
-                             ) -> ProblemConfig:
-    """返回带域随机化标量的新配置；不修改全局默认配置。"""
-    _rng = Random(seed)  # 固定种子留作兼容：真实随机化在 make_scene 内完成
-    field = base.field
-    if bearing_error_half_deg is None:
-        bearing_error_half_deg = field.bearing_error_half_deg
-    if r_eff_range is not None:
-        lo, hi = r_eff_range
-        if not 0 <= lo <= hi:
-            raise ValueError("r_eff_range 必须为递增非负区间")
-    return dataclasses.replace(base, field=dataclasses.replace(
-        field, bearing_error_half_deg=float(bearing_error_half_deg)))
-
-
-__all__ = ["randomize_problem_config"]

project/train/optuna_tune.py

@@ -1,20 +0,0 @@
-"""兼容入口：调用 scripts/tune_hrl.py（P2 后启用）。"""
-from __future__ import annotations
-
-import importlib.util
-from pathlib import Path
-
-
-def run_tuning(argv=None) -> int:
-    path = Path(__file__).resolve().parents[2] / "scripts" / "tune_hrl.py"
-    if not path.exists():
-        raise NotImplementedError(
-            "scripts/tune_hrl.py 尚未实现；P1 阶段先冻结超参并留待 P2。")
-    spec = importlib.util.spec_from_file_location("tune_hrl_compat", path)
-    module = importlib.util.module_from_spec(spec)
-    assert spec.loader is not None
-    spec.loader.exec_module(module)
-    return int(module.main(argv))
-
-
-__all__ = ["run_tuning"]