强化学习第二版

scripts/benchmark_rl.py

@@ -94,6 +94,9 @@ def main(argv=None) -> int:
                   for row in rows]
         cleared = all(row["rl"]["all_cleared"] and row[baseline]["all_cleared"]
                       for row in rows)
+        valid = all(part['completed'] and part['all_cleared'] and part['correct_absence']
+                    and part['normal_exit'] and not part['anomalies'] and not part['timing_mismatches']
+                    for row in rows for part in (row[baseline],row['rl']))
         report[key + "_summary"] = {
             "mean_virtual_s": {
                 baseline: statistics.mean(row[baseline]["virtual_time_s"] for row in rows),
@@ -107,6 +110,7 @@ def main(argv=None) -> int:
                 "rl": statistics.mean(row["rl"]["measures"] for row in rows),
             },
             "all_cleared": cleared,
+            "all_valid": valid,
         }
     output = Path(args.output)
     output.parent.mkdir(parents=True, exist_ok=True)
@@ -116,7 +120,7 @@ def main(argv=None) -> int:
                       "q3": report["q3_summary"],
                       "q4": report["q4_summary"]},
                      ensure_ascii=False, indent=2))
-    return 0
+    return 0 if report['q3_summary']['all_valid'] and report['q4_summary']['all_valid'] else 1
 
 
 if __name__ == "__main__":