This commit is contained in:
Horldsence
2026-09-11 21:00:39 +08:00
parent 2a3ead5d3d
commit 1725cd0891
168 changed files with 170687 additions and 874 deletions
+3
View File
@@ -0,0 +1,3 @@
from .heuristic import HeuristicHRL, run_heuristic
__all__ = ["HeuristicHRL", "run_heuristic"]
+16
View File
@@ -0,0 +1,16 @@
"""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"]
+16
View File
@@ -0,0 +1,16 @@
"""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):
"""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"]