Upload folder using huggingface_hub

app/environment/core.py

@@ -1,6 +1,6 @@
 import json
 from pathlib import Path
-from typing import Any
+from typing import Any, Literal, cast
 
 from app.environment.graders import grade_task
 from app.environment.scenarios.accident import generate_accident_case
@@ -84,9 +84,9 @@ class EmergencyEnv:
             seed=seed,
             task_id=resolved_task_id,
             task_objective=TASKS[resolved_task_id]["objective"],
-            scenario_type=scenario_type,
+            scenario_type=cast(Literal["medical", "accident", "fire"], scenario_type),
             scenario_name=scenario["scenario_name"],
-            scenario_difficulty=difficulty,
+            scenario_difficulty=cast(Literal["easy", "medium", "hard"], difficulty),
             patient_condition=scenario["patient_condition"],
             required_specialization=scenario["required_specialization"],
             initial_critical_time_limit_minutes=scenario["critical_time_limit_minutes"],
@@ -121,7 +121,7 @@ class EmergencyEnv:
 
         self.last_info = StepInfo(
             task_id=resolved_task_id,
-            difficulty=difficulty,
+            difficulty=cast(Literal["easy", "medium", "hard"], difficulty),
             objective=TASKS[resolved_task_id]["objective"],
             progress_score=MIN_REWARD,
             reward_model=RewardModel(
@@ -174,7 +174,7 @@ class EmergencyEnv:
         was_failed_before = selected.hospital_id in self.state_data.failed_hospitals
 
         original_traffic = selected.traffic
-        selected.traffic = self._traffic_shift(selected.traffic, self.state_data.scenario_difficulty)
+        selected.traffic = cast(Literal["low", "medium", "high"], self._traffic_shift(selected.traffic, self.state_data.scenario_difficulty))
 
         speed = compute_speed_kmh(self.base_speed_kmh, selected.traffic)
         travel_time = compute_travel_time_minutes(selected.distance_km, speed)
@@ -288,9 +288,11 @@ class EmergencyEnv:
         )
 
         info = self.last_info.model_dump() if self.last_info else {}
+        # Clamp reward into the strict open interval (0, 1) for the external validator.
+        clamped_reward = max(MIN_REWARD, min(MAX_REWARD, reward))
         return {
             "observation": self._build_observation(),
-            "reward": reward,
+            "reward": clamped_reward,
             "done": self.state_data.done,
             "info": info,
         }
@@ -303,12 +305,11 @@ class EmergencyEnv:
             return Action(step=self.state_data.step, hospital_id=action, rationale="policy selection")
         if isinstance(action, dict):
             assert self.state_data is not None
-            payload = {
-                "step": action.get("step", self.state_data.step),
-                "hospital_id": action.get("hospital_id"),
-                "rationale": action.get("rationale"),
-            }
-            return Action(**payload)
+            return Action(
+                step=action.get("step", self.state_data.step),
+                hospital_id=str(action.get("hospital_id", "")),
+                rationale=action.get("rationale"),
+            )
         raise ValueError("Action must be Action, hospital_id string, or action dict.")
 
     def _build_hospital_states(self, scenario: dict[str, Any]) -> list[HospitalState]:
@@ -388,8 +389,8 @@ class EmergencyEnv:
                     distance_km=distance,
                     icu_display=icu_display,
                     icu_actual=icu_actual,
-                    specialization=specialization,
-                    traffic=traffic,
+                    specialization=cast(Literal["cardiac", "trauma", "general"], specialization),
+                    traffic=cast(Literal["low", "medium", "high"], traffic),
                 )
             )
             extra_count += 1
@@ -444,18 +445,18 @@ class EmergencyEnv:
         )
         reward = max(MIN_REWARD, min(MAX_REWARD, reward))
 
+        raw_delay = (
+            unknown_critical_penalty
+            + repeat_penalty
+            + failed_repeat_penalty
+            + traffic_penalty
+            + hidden_case_penalty
+        )
         breakdown = RewardBreakdown(
             survival_component=max(MIN_REWARD, min(MAX_REWARD, (status_reward + 0.5) / 1.5)),
             time_efficiency_component=max(MIN_REWARD, min(MAX_REWARD, 1.0 - (travel_time / 25.0))),
-            specialization_component=(MAX_REWARD if self._specialization_match(selected) else 0.4),
-            delay_penalty=min(
-                MAX_REWARD,
-                unknown_critical_penalty
-                + repeat_penalty
-                + failed_repeat_penalty
-                + traffic_penalty
-                + hidden_case_penalty,
-            ),
+            specialization_component=max(MIN_REWARD, min(MAX_REWARD, MAX_REWARD if self._specialization_match(selected) else 0.4)),
+            delay_penalty=max(MIN_REWARD, min(MAX_REWARD, raw_delay)),
         )
 
         return reward, breakdown
@@ -1019,7 +1020,7 @@ class EmergencyEnv:
         assert self.state_data is not None
         for hospital in self.state_data.hospitals:
             if self._rng.random() < 0.40:
-                hospital.traffic = self._traffic_shift(hospital.traffic, self.state_data.scenario_difficulty)
+                hospital.traffic = cast(Literal["low", "medium", "high"], self._traffic_shift(hospital.traffic, self.state_data.scenario_difficulty))
 
             if self._rng.random() < DifficultyModifier.get_icu_mismatch_probability(self.state_data.scenario_difficulty):
                 hospital.icu_actual = not hospital.icu_actual
@@ -1082,7 +1083,9 @@ class EmergencyEnv:
 
     def _update_learning_memory(self, hospital_id: str, success: bool, reward: float) -> None:
         memory = self._load_memory()
-        entry = memory.get(hospital_id, LearningEntry())
+        entry = memory.get(hospital_id)
+        if entry is None:
+            entry = LearningEntry()
 
         if success:
             entry.success += 1
@@ -1113,7 +1116,7 @@ class EmergencyEnv:
         progress_component = self._progress_score()
         reward_component = max(MIN_REWARD, min(MAX_REWARD, self.state_data.reward))
         score = 0.15 + (0.35 * reward_component) + (0.25 * progress_component)
-        return max(0.1, min(0.85, score))
+        return max(MIN_REWARD, min(MAX_REWARD, max(0.1, min(0.85, score))))
 
     def _success_score(self) -> float:
         assert self.state_data is not None
@@ -1123,7 +1126,7 @@ class EmergencyEnv:
         rejected_steps = sum(1 for item in self.trajectory if item.get("outcome_status") == "rejected")
         route_quality = max(0.0, 1.0 - (rejected_steps / total_steps))
         score = (0.45 * reward_component) + (0.40 * progress_component) + (0.15 * route_quality)
-        return max(0.25, min(0.99, score))
+        return max(MIN_REWARD, min(MAX_REWARD, max(0.25, min(0.99, score))))
 
 
 ACDEEnvironment = EmergencyEnv

app/models/reward.py

@@ -1,35 +1,73 @@
-from typing import Literal
-
-from pydantic import BaseModel, Field
-
-
-class RewardBreakdown(BaseModel):
-    survival_component: float = Field(gt=0.0, lt=1.0)
-    time_efficiency_component: float = Field(gt=0.0, lt=1.0)
-    specialization_component: float = Field(gt=0.0, lt=1.0)
-    delay_penalty: float = Field(gt=0.0, lt=1.0)
-
-
-class RewardModel(BaseModel):
-    value: float = Field(gt=0.0, lt=1.0)
-    breakdown: RewardBreakdown
-
-
-class GraderResult(BaseModel):
-    task_id: Literal["acde_easy", "acde_medium", "acde_hard"]
-    difficulty: Literal["easy", "medium", "hard"]
-    objective: str
-    score: float = Field(gt=0.0, lt=1.0)
-    passed: bool
-    criteria: dict[str, float] = Field(default_factory=dict)
-
-
-class StepInfo(BaseModel):
-    last_action_error: str | None = None
-    task_id: Literal["acde_easy", "acde_medium", "acde_hard"]
-    difficulty: Literal["easy", "medium", "hard"]
-    objective: str
-    progress_score: float = Field(gt=0.0, lt=1.0)
-    reward_model: RewardModel
-    grader: GraderResult | None = None
-    outcome: dict[str, str] | None = None
+from typing import Literal
+
+from pydantic import BaseModel, Field, field_validator
+
+
+# Strict boundaries for all score-like fields.
+# The external validator requires scores strictly between 0 and 1
+# (not 0.0 and not 1.0), so we clamp all values to [0.001, 0.999].
+_FLOOR = 0.001
+_CEIL = 0.999
+
+
+def _clamp(v: float) -> float:
+    """Clamp a score to the open interval (0, 1)."""
+    return max(_FLOOR, min(_CEIL, v))
+
+
+class RewardBreakdown(BaseModel):
+    survival_component: float = Field(ge=_FLOOR, le=_CEIL)
+    time_efficiency_component: float = Field(ge=_FLOOR, le=_CEIL)
+    specialization_component: float = Field(ge=_FLOOR, le=_CEIL)
+    delay_penalty: float = Field(ge=_FLOOR, le=_CEIL)
+
+    @field_validator(
+        "survival_component",
+        "time_efficiency_component",
+        "specialization_component",
+        "delay_penalty",
+        mode="before",
+    )
+    @classmethod
+    def clamp_score(cls, v: float) -> float:
+        return _clamp(v)
+
+
+class RewardModel(BaseModel):
+    value: float = Field(ge=_FLOOR, le=_CEIL)
+    breakdown: RewardBreakdown
+
+    @field_validator("value", mode="before")
+    @classmethod
+    def clamp_value(cls, v: float) -> float:
+        return _clamp(v)
+
+
+class GraderResult(BaseModel):
+    task_id: Literal["acde_easy", "acde_medium", "acde_hard"]
+    difficulty: Literal["easy", "medium", "hard"]
+    objective: str
+    score: float = Field(ge=_FLOOR, le=_CEIL)
+    passed: bool
+    criteria: dict[str, float] = Field(default_factory=dict)
+
+    @field_validator("score", mode="before")
+    @classmethod
+    def clamp_score(cls, v: float) -> float:
+        return _clamp(v)
+
+
+class StepInfo(BaseModel):
+    last_action_error: str | None = None
+    task_id: Literal["acde_easy", "acde_medium", "acde_hard"]
+    difficulty: Literal["easy", "medium", "hard"]
+    objective: str
+    progress_score: float = Field(ge=_FLOOR, le=_CEIL)
+    reward_model: RewardModel
+    grader: GraderResult | None = None
+    outcome: dict[str, str] | None = None
+
+    @field_validator("progress_score", mode="before")
+    @classmethod
+    def clamp_progress(cls, v: float) -> float:
+        return _clamp(v)

app/models/state.py

@@ -56,8 +56,8 @@ class EnvState(BaseModel):
     selected_hospital_id: str | None = None
     done: bool = False
     final_outcome: Literal["SUCCESS", "FAILURE"] | None = None
-    final_score: float = Field(default=0.0, ge=0.0, le=1.0)
-    reward: float = Field(default=0.0, ge=0.0, le=1.0)
+    final_score: float = Field(default=0.001, ge=0.001, le=0.999)
+    reward: float = Field(default=0.001, ge=0.001, le=0.999)
     ambulance_status: Literal["en_route", "in_transit", "arrived", "admitted", "rerouting"] = "en_route"
     current_location_context: str = "incident_site"
     visited_hospitals: list[str] = Field(default_factory=list)

data/learning_archive.json

@@ -7370,6 +7370,722 @@
       "best_scenario_name": "Bridge Crash (Infrastructure Blocked)",
       "best_difficulty": "hard",
       "best_required_specialization": "trauma"
+    },
+    "865967163|acde_easy": {
+      "attempts": 1,
+      "best_score": 0.7872000000000001,
+      "best_actions": [
+        "H4",
+        "H1"
+      ],
+      "best_steps": 2,
+      "step_stats": {
+        "1": {
+          "H4": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 1,
+            "rejected": 0,
+            "total_reward": 0.274,
+            "avg_reward": 0.274,
+            "last_status": "PARTIAL",
+            "last_reason": "Critical deterioration managed temporarily; reroute still needed",
+            "success_rate": 0.0
+          }
+        },
+        "2": {
+          "H1": {
+            "count": 1,
+            "success": 1,
+            "accepted": 1,
+            "partial": 0,
+            "rejected": 0,
+            "total_reward": 0.8960000000000001,
+            "avg_reward": 0.8960000000000001,
+            "last_status": "ACCEPTED",
+            "last_reason": "Patient stabilized after delayed admission",
+            "success_rate": 1.0
+          }
+        }
+      },
+      "last_score": 0.7872000000000001,
+      "last_success": true,
+      "last_run_at": "2026-04-09T05:14:40.441962+00:00",
+      "last_actions": [
+        "H4",
+        "H1"
+      ],
+      "last_required_specialization": "trauma",
+      "last_scenario_type": "accident",
+      "last_scenario_name": "Highway Collision (Severe)",
+      "best_success": true,
+      "best_scenario_name": "Highway Collision (Severe)",
+      "best_difficulty": "easy",
+      "best_required_specialization": "trauma"
+    },
+    "865967164|acde_medium": {
+      "attempts": 1,
+      "best_score": 0.48340000000000005,
+      "best_actions": [
+        "H3",
+        "H2",
+        "H3"
+      ],
+      "best_steps": 3,
+      "step_stats": {
+        "1": {
+          "H3": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 1,
+            "rejected": 0,
+            "total_reward": 0.4690000000000001,
+            "avg_reward": 0.4690000000000001,
+            "last_status": "PARTIAL",
+            "last_reason": "Admitted with delays: doctor delayed",
+            "success_rate": 0.0
+          }
+        },
+        "2": {
+          "H2": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 0,
+            "rejected": 1,
+            "total_reward": 0.079,
+            "avg_reward": 0.079,
+            "last_status": "REJECTED",
+            "last_reason": "Hospital cannot admit: ICU unavailable",
+            "success_rate": 0.0
+          }
+        },
+        "3": {
+          "H3": {
+            "count": 1,
+            "success": 1,
+            "accepted": 1,
+            "partial": 0,
+            "rejected": 0,
+            "total_reward": 0.532,
+            "avg_reward": 0.532,
+            "last_status": "ACCEPTED",
+            "last_reason": "Condition stabilized after progressive treatment",
+            "success_rate": 1.0
+          }
+        }
+      },
+      "last_score": 0.48340000000000005,
+      "last_success": true,
+      "last_run_at": "2026-04-09T05:14:41.433914+00:00",
+      "last_actions": [
+        "H3",
+        "H2",
+        "H3"
+      ],
+      "last_required_specialization": "trauma",
+      "last_scenario_type": "accident",
+      "last_scenario_name": "Urban Pile-up (Rush Hour)",
+      "best_success": true,
+      "best_scenario_name": "Urban Pile-up (Rush Hour)",
+      "best_difficulty": "medium",
+      "best_required_specialization": "trauma"
+    },
+    "865967165|acde_hard": {
+      "attempts": 1,
+      "best_score": 0.15059999999999998,
+      "best_actions": [
+        "H6",
+        "H2",
+        "H6",
+        "H3"
+      ],
+      "best_steps": 4,
+      "step_stats": {
+        "1": {
+          "H6": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 0,
+            "rejected": 1,
+            "total_reward": 0.001,
+            "avg_reward": 0.001,
+            "last_status": "REJECTED",
+            "last_reason": "Hospital cannot admit: ICU unavailable",
+            "success_rate": 0.0
+          }
+        },
+        "2": {
+          "H2": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 0,
+            "rejected": 1,
+            "total_reward": 0.001,
+            "avg_reward": 0.001,
+            "last_status": "REJECTED",
+            "last_reason": "Hospital cannot admit: No specialist available",
+            "success_rate": 0.0
+          }
+        },
+        "3": {
+          "H6": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 0,
+            "rejected": 1,
+            "total_reward": 0.001,
+            "avg_reward": 0.001,
+            "last_status": "REJECTED",
+            "last_reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required.",
+            "success_rate": 0.0
+          }
+        },
+        "4": {
+          "H3": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 0,
+            "rejected": 1,
+            "total_reward": 0.001,
+            "avg_reward": 0.001,
+            "last_status": "REJECTED",
+            "last_reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required.",
+            "success_rate": 0.0
+          }
+        }
+      },
+      "last_score": 0.15059999999999998,
+      "last_success": false,
+      "last_run_at": "2026-04-09T05:14:43.050718+00:00",
+      "last_actions": [
+        "H6",
+        "H2",
+        "H6",
+        "H3"
+      ],
+      "last_required_specialization": "trauma",
+      "last_scenario_type": "accident",
+      "last_scenario_name": "Bridge Crash (Infrastructure Blocked)",
+      "best_success": false,
+      "best_scenario_name": "Bridge Crash (Infrastructure Blocked)",
+      "best_difficulty": "hard",
+      "best_required_specialization": "trauma"
+    },
+    "562874771|acde_easy": {
+      "attempts": 1,
+      "best_score": 0.4838,
+      "best_actions": [
+        "H4",
+        "H1",
+        "H4"
+      ],
+      "best_steps": 3,
+      "step_stats": {
+        "1": {
+          "H4": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 1,
+            "rejected": 0,
+            "total_reward": 0.234,
+            "avg_reward": 0.234,
+            "last_status": "PARTIAL",
+            "last_reason": "Critical deterioration managed temporarily; reroute still needed",
+            "success_rate": 0.0
+          }
+        },
+        "2": {
+          "H1": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 0,
+            "rejected": 1,
+            "total_reward": 0.008999999999999996,
+            "avg_reward": 0.008999999999999996,
+            "last_status": "REJECTED",
+            "last_reason": "Condition became irreversible after delays",
+            "success_rate": 0.0
+          }
+        },
+        "3": {
+          "H4": {
+            "count": 1,
+            "success": 1,
+            "accepted": 1,
+            "partial": 0,
+            "rejected": 0,
+            "total_reward": 0.6023999999999999,
+            "avg_reward": 0.6023999999999999,
+            "last_status": "ACCEPTED",
+            "last_reason": "Emergency stabilization at last attempt",
+            "success_rate": 1.0
+          }
+        }
+      },
+      "last_score": 0.4838,
+      "last_success": true,
+      "last_run_at": "2026-04-09T05:18:04.053307+00:00",
+      "last_actions": [
+        "H4",
+        "H1",
+        "H4"
+      ],
+      "last_required_specialization": "cardiac",
+      "last_scenario_type": "medical",
+      "last_scenario_name": "Heart Attack (Critical)",
+      "best_success": true,
+      "best_scenario_name": "Heart Attack (Critical)",
+      "best_difficulty": "easy",
+      "best_required_specialization": "cardiac"
+    },
+    "562874772|acde_medium": {
+      "attempts": 1,
+      "best_score": 0.9226500000000001,
+      "best_actions": [
+        "H5"
+      ],
+      "best_steps": 1,
+      "step_stats": {
+        "1": {
+          "H5": {
+            "count": 1,
+            "success": 1,
+            "accepted": 1,
+            "partial": 0,
+            "rejected": 0,
+            "total_reward": 0.909,
+            "avg_reward": 0.909,
+            "last_status": "ACCEPTED",
+            "last_reason": "Patient admitted and treatment began",
+            "success_rate": 1.0
+          }
+        }
+      },
+      "last_score": 0.9226500000000001,
+      "last_success": true,
+      "last_run_at": "2026-04-09T05:18:04.467741+00:00",
+      "last_actions": [
+        "H5"
+      ],
+      "last_required_specialization": "cardiac",
+      "last_scenario_type": "medical",
+      "last_scenario_name": "Heart Attack (Unstable)",
+      "best_success": true,
+      "best_scenario_name": "Heart Attack (Unstable)",
+      "best_difficulty": "medium",
+      "best_required_specialization": "cardiac"
+    },
+    "562874773|acde_hard": {
+      "attempts": 1,
+      "best_score": 0.17603749999999999,
+      "best_actions": [
+        "H6",
+        "H1",
+        "H4",
+        "H3"
+      ],
+      "best_steps": 4,
+      "step_stats": {
+        "1": {
+          "H6": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 0,
+            "rejected": 1,
+            "total_reward": 0.001,
+            "avg_reward": 0.001,
+            "last_status": "REJECTED",
+            "last_reason": "Hospital cannot admit: Hospital overloaded",
+            "success_rate": 0.0
+          }
+        },
+        "2": {
+          "H1": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 1,
+            "rejected": 0,
+            "total_reward": 0.40800000000000014,
+            "avg_reward": 0.40800000000000014,
+            "last_status": "PARTIAL",
+            "last_reason": "Admitted with delays: prolonged transfer strain",
+            "success_rate": 0.0
+          }
+        },
+        "3": {
+          "H4": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 0,
+            "rejected": 1,
+            "total_reward": 0.001,
+            "avg_reward": 0.001,
+            "last_status": "REJECTED",
+            "last_reason": "Hospital cannot admit: ICU unavailable, No specialist available",
+            "success_rate": 0.0
+          }
+        },
+        "4": {
+          "H3": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 0,
+            "rejected": 1,
+            "total_reward": 0.001,
+            "avg_reward": 0.001,
+            "last_status": "REJECTED",
+            "last_reason": "Hospital cannot admit: No specialist available",
+            "success_rate": 0.0
+          }
+        }
+      },
+      "last_score": 0.17603749999999999,
+      "last_success": false,
+      "last_run_at": "2026-04-09T05:18:06.091131+00:00",
+      "last_actions": [
+        "H6",
+        "H1",
+        "H4",
+        "H3"
+      ],
+      "last_required_specialization": "general",
+      "last_scenario_type": "fire",
+      "last_scenario_name": "Wildfire Front (Evacuation Gridlock)",
+      "best_success": false,
+      "best_scenario_name": "Wildfire Front (Evacuation Gridlock)",
+      "best_difficulty": "hard",
+      "best_required_specialization": "general"
+    },
+    "850880720|acde_easy": {
+      "attempts": 1,
+      "best_score": 0.99,
+      "best_actions": [
+        "H3"
+      ],
+      "best_steps": 1,
+      "step_stats": {
+        "1": {
+          "H3": {
+            "count": 1,
+            "success": 1,
+            "accepted": 1,
+            "partial": 0,
+            "rejected": 0,
+            "total_reward": 0.999,
+            "avg_reward": 0.999,
+            "last_status": "ACCEPTED",
+            "last_reason": "Patient admitted and treatment began",
+            "success_rate": 1.0
+          }
+        }
+      },
+      "last_score": 0.99,
+      "last_success": true,
+      "last_run_at": "2026-04-09T05:18:37.126090+00:00",
+      "last_actions": [
+        "H3"
+      ],
+      "last_required_specialization": "general",
+      "last_scenario_type": "fire",
+      "last_scenario_name": "Apartment Fire (Smoke Inhalation)",
+      "best_success": true,
+      "best_scenario_name": "Apartment Fire (Smoke Inhalation)",
+      "best_difficulty": "easy",
+      "best_required_specialization": "general"
+    },
+    "850880721|acde_medium": {
+      "attempts": 1,
+      "best_score": 0.16988124999999998,
+      "best_actions": [
+        "H2",
+        "H3",
+        "H5",
+        "H3"
+      ],
+      "best_steps": 4,
+      "step_stats": {
+        "1": {
+          "H2": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 1,
+            "rejected": 0,
+            "total_reward": 0.13650000000000004,
+            "avg_reward": 0.13650000000000004,
+            "last_status": "PARTIAL",
+            "last_reason": "Admitted with delays: prolonged transfer strain, hospital busy but manageable",
+            "success_rate": 0.0
+          }
+        },
+        "2": {
+          "H3": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 1,
+            "rejected": 0,
+            "total_reward": 0.17400000000000002,
+            "avg_reward": 0.17400000000000002,
+            "last_status": "PARTIAL",
+            "last_reason": "Condition worsened but remains temporarily transferable",
+            "success_rate": 0.0
+          }
+        },
+        "3": {
+          "H5": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 0,
+            "rejected": 1,
+            "total_reward": 0.001,
+            "avg_reward": 0.001,
+            "last_status": "REJECTED",
+            "last_reason": "Doctor was reassigned to another emergency at arrival",
+            "success_rate": 0.0
+          }
+        },
+        "4": {
+          "H3": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 0,
+            "rejected": 1,
+            "total_reward": 0.001,
+            "avg_reward": 0.001,
+            "last_status": "REJECTED",
+            "last_reason": "Condition became non-transferable during delay; immediate critical care failed",
+            "success_rate": 0.0
+          }
+        }
+      },
+      "last_score": 0.16988124999999998,
+      "last_success": false,
+      "last_run_at": "2026-04-09T05:18:38.648867+00:00",
+      "last_actions": [
+        "H2",
+        "H3",
+        "H5",
+        "H3"
+      ],
+      "last_required_specialization": "cardiac",
+      "last_scenario_type": "medical",
+      "last_scenario_name": "Heart Attack (Unstable)",
+      "best_success": false,
+      "best_scenario_name": "Heart Attack (Unstable)",
+      "best_difficulty": "medium",
+      "best_required_specialization": "cardiac"
+    },
+    "850880722|acde_hard": {
+      "attempts": 1,
+      "best_score": 0.45350000000000007,
+      "best_actions": [
+        "H3",
+        "H5"
+      ],
+      "best_steps": 2,
+      "step_stats": {
+        "1": {
+          "H3": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 0,
+            "rejected": 1,
+            "total_reward": 0.001,
+            "avg_reward": 0.001,
+            "last_status": "REJECTED",
+            "last_reason": "Hospital cannot admit: ICU unavailable",
+            "success_rate": 0.0
+          }
+        },
+        "2": {
+          "H5": {
+            "count": 1,
+            "success": 1,
+            "accepted": 1,
+            "partial": 0,
+            "rejected": 0,
+            "total_reward": 0.5820000000000001,
+            "avg_reward": 0.5820000000000001,
+            "last_status": "ACCEPTED",
+            "last_reason": "Condition stabilized after progressive treatment",
+            "success_rate": 1.0
+          }
+        }
+      },
+      "last_score": 0.45350000000000007,
+      "last_success": true,
+      "last_run_at": "2026-04-09T05:18:39.464469+00:00",
+      "last_actions": [
+        "H3",
+        "H5"
+      ],
+      "last_required_specialization": "cardiac",
+      "last_scenario_type": "medical",
+      "last_scenario_name": "Mass Cardiac Event (Overload)",
+      "best_success": true,
+      "best_scenario_name": "Mass Cardiac Event (Overload)",
+      "best_difficulty": "hard",
+      "best_required_specialization": "cardiac"
+    },
+    "600335717|acde_easy": {
+      "attempts": 1,
+      "best_score": 0.2334,
+      "best_actions": [
+        "H1"
+      ],
+      "best_steps": 1,
+      "step_stats": {
+        "1": {
+          "H1": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 0,
+            "rejected": 1,
+            "total_reward": 0.139,
+            "avg_reward": 0.139,
+            "last_status": "REJECTED",
+            "last_reason": "Condition became non-transferable during delay; immediate critical care failed",
+            "success_rate": 0.0
+          }
+        }
+      },
+      "last_score": 0.2334,
+      "last_success": false,
+      "last_run_at": "2026-04-09T05:19:11.834510+00:00",
+      "last_actions": [
+        "H1"
+      ],
+      "last_required_specialization": "cardiac",
+      "last_scenario_type": "medical",
+      "last_scenario_name": "Heart Attack (Critical)",
+      "best_success": false,
+      "best_scenario_name": "Heart Attack (Critical)",
+      "best_difficulty": "easy",
+      "best_required_specialization": "cardiac"
+    },
+    "600335718|acde_medium": {
+      "attempts": 1,
+      "best_score": 0.43220000000000003,
+      "best_actions": [
+        "H2",
+        "H4"
+      ],
+      "best_steps": 2,
+      "step_stats": {
+        "1": {
+          "H2": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 0,
+            "rejected": 1,
+            "total_reward": 0.109,
+            "avg_reward": 0.109,
+            "last_status": "REJECTED",
+            "last_reason": "Hospital cannot admit: ICU unavailable",
+            "success_rate": 0.0
+          }
+        },
+        "2": {
+          "H4": {
+            "count": 1,
+            "success": 1,
+            "accepted": 1,
+            "partial": 0,
+            "rejected": 0,
+            "total_reward": 0.516,
+            "avg_reward": 0.516,
+            "last_status": "ACCEPTED",
+            "last_reason": "Patient stabilized after delayed admission",
+            "success_rate": 1.0
+          }
+        }
+      },
+      "last_score": 0.43220000000000003,
+      "last_success": true,
+      "last_run_at": "2026-04-09T05:19:12.461036+00:00",
+      "last_actions": [
+        "H2",
+        "H4"
+      ],
+      "last_required_specialization": "trauma",
+      "last_scenario_type": "accident",
+      "last_scenario_name": "Urban Pile-up (Rush Hour)",
+      "best_success": true,
+      "best_scenario_name": "Urban Pile-up (Rush Hour)",
+      "best_difficulty": "medium",
+      "best_required_specialization": "trauma"
+    },
+    "600335719|acde_hard": {
+      "attempts": 1,
+      "best_score": 0.15059999999999998,
+      "best_actions": [
+        "H6",
+        "H5"
+      ],
+      "best_steps": 2,
+      "step_stats": {
+        "1": {
+          "H6": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 0,
+            "rejected": 1,
+            "total_reward": 0.001,
+            "avg_reward": 0.001,
+            "last_status": "REJECTED",
+            "last_reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required.",
+            "success_rate": 0.0
+          }
+        },
+        "2": {
+          "H5": {
+            "count": 1,
+            "success": 0,
+            "accepted": 0,
+            "partial": 0,
+            "rejected": 1,
+            "total_reward": 0.001,
+            "avg_reward": 0.001,
+            "last_status": "REJECTED",
+            "last_reason": "Condition became non-transferable during delay; immediate critical care failed",
+            "success_rate": 0.0
+          }
+        }
+      },
+      "last_score": 0.15059999999999998,
+      "last_success": false,
+      "last_run_at": "2026-04-09T05:19:13.261267+00:00",
+      "last_actions": [
+        "H6",
+        "H5"
+      ],
+      "last_required_specialization": "general",
+      "last_scenario_type": "fire",
+      "last_scenario_name": "Wildfire Front (Evacuation Gridlock)",
+      "best_success": false,
+      "best_scenario_name": "Wildfire Front (Evacuation Gridlock)",
+      "best_difficulty": "hard",
+      "best_required_specialization": "general"
     }
   },
   "episodes": [
@@ -9248,6 +9964,179 @@
         "H5"
       ],
       "timestamp": "2026-04-09T04:57:26.758443+00:00"
+    },
+    {
+      "seed": 865967163,
+      "task_id": "acde_easy",
+      "difficulty": "easy",
+      "required_specialization": "trauma",
+      "scenario_name": "Highway Collision (Severe)",
+      "score": 0.7872000000000001,
+      "success": true,
+      "actions": [
+        "H4",
+        "H1"
+      ],
+      "timestamp": "2026-04-09T05:14:40.441962+00:00"
+    },
+    {
+      "seed": 865967164,
+      "task_id": "acde_medium",
+      "difficulty": "medium",
+      "required_specialization": "trauma",
+      "scenario_name": "Urban Pile-up (Rush Hour)",
+      "score": 0.48340000000000005,
+      "success": true,
+      "actions": [
+        "H3",
+        "H2",
+        "H3"
+      ],
+      "timestamp": "2026-04-09T05:14:41.433914+00:00"
+    },
+    {
+      "seed": 865967165,
+      "task_id": "acde_hard",
+      "difficulty": "hard",
+      "required_specialization": "trauma",
+      "scenario_name": "Bridge Crash (Infrastructure Blocked)",
+      "score": 0.15059999999999998,
+      "success": false,
+      "actions": [
+        "H6",
+        "H2",
+        "H6",
+        "H3"
+      ],
+      "timestamp": "2026-04-09T05:14:43.050718+00:00"
+    },
+    {
+      "seed": 562874771,
+      "task_id": "acde_easy",
+      "difficulty": "easy",
+      "required_specialization": "cardiac",
+      "scenario_name": "Heart Attack (Critical)",
+      "score": 0.4838,
+      "success": true,
+      "actions": [
+        "H4",
+        "H1",
+        "H4"
+      ],
+      "timestamp": "2026-04-09T05:18:04.053307+00:00"
+    },
+    {
+      "seed": 562874772,
+      "task_id": "acde_medium",
+      "difficulty": "medium",
+      "required_specialization": "cardiac",
+      "scenario_name": "Heart Attack (Unstable)",
+      "score": 0.9226500000000001,
+      "success": true,
+      "actions": [
+        "H5"
+      ],
+      "timestamp": "2026-04-09T05:18:04.467741+00:00"
+    },
+    {
+      "seed": 562874773,
+      "task_id": "acde_hard",
+      "difficulty": "hard",
+      "required_specialization": "general",
+      "scenario_name": "Wildfire Front (Evacuation Gridlock)",
+      "score": 0.17603749999999999,
+      "success": false,
+      "actions": [
+        "H6",
+        "H1",
+        "H4",
+        "H3"
+      ],
+      "timestamp": "2026-04-09T05:18:06.091131+00:00"
+    },
+    {
+      "seed": 850880720,
+      "task_id": "acde_easy",
+      "difficulty": "easy",
+      "required_specialization": "general",
+      "scenario_name": "Apartment Fire (Smoke Inhalation)",
+      "score": 0.99,
+      "success": true,
+      "actions": [
+        "H3"
+      ],
+      "timestamp": "2026-04-09T05:18:37.126090+00:00"
+    },
+    {
+      "seed": 850880721,
+      "task_id": "acde_medium",
+      "difficulty": "medium",
+      "required_specialization": "cardiac",
+      "scenario_name": "Heart Attack (Unstable)",
+      "score": 0.16988124999999998,
+      "success": false,
+      "actions": [
+        "H2",
+        "H3",
+        "H5",
+        "H3"
+      ],
+      "timestamp": "2026-04-09T05:18:38.648867+00:00"
+    },
+    {
+      "seed": 850880722,
+      "task_id": "acde_hard",
+      "difficulty": "hard",
+      "required_specialization": "cardiac",
+      "scenario_name": "Mass Cardiac Event (Overload)",
+      "score": 0.45350000000000007,
+      "success": true,
+      "actions": [
+        "H3",
+        "H5"
+      ],
+      "timestamp": "2026-04-09T05:18:39.464469+00:00"
+    },
+    {
+      "seed": 600335717,
+      "task_id": "acde_easy",
+      "difficulty": "easy",
+      "required_specialization": "cardiac",
+      "scenario_name": "Heart Attack (Critical)",
+      "score": 0.2334,
+      "success": false,
+      "actions": [
+        "H1"
+      ],
+      "timestamp": "2026-04-09T05:19:11.834510+00:00"
+    },
+    {
+      "seed": 600335718,
+      "task_id": "acde_medium",
+      "difficulty": "medium",
+      "required_specialization": "trauma",
+      "scenario_name": "Urban Pile-up (Rush Hour)",
+      "score": 0.43220000000000003,
+      "success": true,
+      "actions": [
+        "H2",
+        "H4"
+      ],
+      "timestamp": "2026-04-09T05:19:12.461036+00:00"
+    },
+    {
+      "seed": 600335719,
+      "task_id": "acde_hard",
+      "difficulty": "hard",
+      "required_specialization": "general",
+      "scenario_name": "Wildfire Front (Evacuation Gridlock)",
+      "score": 0.15059999999999998,
+      "success": false,
+      "actions": [
+        "H6",
+        "H5"
+      ],
+      "timestamp": "2026-04-09T05:19:13.261267+00:00"
     }
   ]
 }

data/learning_memory.json

@@ -1,44 +1,44 @@
 {
   "H2": {
-    "success": 109,
-    "fail": 211,
-    "avg": 0.3393390625000006,
-    "accepted": 109,
-    "rejected": 211
+    "success": 110,
+    "fail": 212,
+    "avg": 0.337900621118013,
+    "accepted": 110,
+    "rejected": 212
   },
   "H6": {
     "success": 50,
-    "fail": 140,
-    "avg": 0.2986710526315795,
+    "fail": 143,
+    "avg": 0.2940440414507777,
     "accepted": 50,
-    "rejected": 140
+    "rejected": 143
   },
   "H5": {
-    "success": 112,
-    "fail": 176,
-    "avg": 0.38393784722222196,
-    "accepted": 112,
-    "rejected": 176
+    "success": 114,
+    "fail": 178,
+    "avg": 0.38379143835616414,
+    "accepted": 114,
+    "rejected": 178
   },
   "H1": {
-    "success": 110,
-    "fail": 107,
-    "avg": 0.4174359447004605,
-    "accepted": 110,
-    "rejected": 107
+    "success": 111,
+    "fail": 110,
+    "avg": 0.41240090497737525,
+    "accepted": 111,
+    "rejected": 110
   },
   "H3": {
-    "success": 97,
-    "fail": 152,
-    "avg": 0.35650481927710814,
-    "accepted": 97,
-    "rejected": 152
+    "success": 102,
+    "fail": 156,
+    "avg": 0.3559833333333331,
+    "accepted": 102,
+    "rejected": 156
   },
   "H4": {
-    "success": 37,
-    "fail": 102,
-    "avg": 0.3546151079136686,
-    "accepted": 37,
-    "rejected": 102
+    "success": 41,
+    "fail": 105,
+    "avg": 0.34951301369862975,
+    "accepted": 41,
+    "rejected": 105
   }
 }

data/trajectory_history.jsonl

@@ -326,3 +326,32 @@
 {"seed": 44, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.4862574941416685, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.001}
 {"seed": 44, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.07027740357273131, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.001}
 {"seed": 44, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.47341627825998767, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.001}
+{"seed": 865967163, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H4", "policy_score": 0.28522225923842554, "strategy": "safe policy"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.274}
+{"seed": 865967163, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "stable", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": ["H4"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H1", "policy_score": 0.430398797272352, "strategy": "balanced policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.8960000000000001}
+{"seed": 865967164, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.3470070739535391, "strategy": "safe policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: doctor delayed"}, "reward": 0.4690000000000001}
+{"seed": 865967164, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": ["H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.3155267186726896, "strategy": "balanced policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.079}
+{"seed": 865967164, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H3", "H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.4258905882454945, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Condition stabilized after progressive treatment"}, "reward": 0.532}
+{"seed": 865967165, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H6", "policy_score": 0.3076474962108312, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.001}
+{"seed": 865967165, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H6"], "visited_hospitals": ["H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.3035629436259161, "strategy": "risk-aware policy + guided-exploration"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.001}
+{"seed": 865967165, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H6", "H4"], "visited_hospitals": ["H6", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.11129517908464792, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.001}
+{"seed": 865967165, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H6", "H4"], "visited_hospitals": ["H6", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.29586549899480935, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.001}
+{"seed": 562874771, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H4", "policy_score": 0.2712048097577652, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.234}
+{"seed": 562874771, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": ["H4"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H1", "policy_score": 0.35970778218903066, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.008999999999999996}
+{"seed": 562874771, "task": "acde_easy", "difficulty": "easy", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H4", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.4523870351936169, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Emergency stabilization at last attempt"}, "reward": 0.6023999999999999}
+{"seed": 562874772, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.330475874967317, "strategy": "safe policy + critical triage"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.909}
+{"seed": 562874773, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H6", "policy_score": 0.16730626096306447, "strategy": "safe policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.001}
+{"seed": 562874773, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.38920337366242297, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain"}, "reward": 0.40800000000000014}
+{"seed": 562874773, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H5", "H1"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H4", "policy_score": 0.09872350410300806, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": 0.001}
+{"seed": 562874773, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H5", "H4"], "visited_hospitals": ["H5", "H1", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.23065044082853245, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.001}
+{"seed": 850880720, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.29399842964915673, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.999}
+{"seed": 850880721, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.4445027887294011, "strategy": "safe policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain, hospital busy but manageable"}, "reward": 0.13650000000000004}
+{"seed": 850880721, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.4530366133689682, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Condition worsened but remains temporarily transferable"}, "reward": 0.17400000000000002}
+{"seed": 850880721, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": ["H2", "H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H5", "policy_score": 0.36233580012122824, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Doctor was reassigned to another emergency at arrival"}, "reward": 0.001}
+{"seed": 850880721, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H2", "H3", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.2867098759261258, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.001}
+{"seed": 850880722, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.4706955388080195, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.001}
+{"seed": 850880722, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H3"], "visited_hospitals": ["H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.46941242001424005, "strategy": "risk-aware policy"}, "outcome": {"status": "ACCEPTED", "reason": "Condition stabilized after progressive treatment"}, "reward": 0.5820000000000001}
+{"seed": 600335717, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.3186401093335327, "strategy": "safe policy + critical triage + guided-exploration"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.139}
+{"seed": 600335718, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.4037159167006607, "strategy": "safe policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.109}
+{"seed": 600335718, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H4"], "visited_hospitals": ["H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.07313118251968914, "strategy": "risk-aware policy + anti-stupidity guard + immediate-retry override"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.516}
+{"seed": 600335719, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H6", "policy_score": 0.3244976864117649, "strategy": "safe policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.001}
+{"seed": 600335719, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6"], "visited_hospitals": ["H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.2976383394515107, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.001}

openenv.yaml

@@ -24,5 +24,5 @@ contracts:
   reward: app.models.reward.RewardModel
   info: app.models.reward.StepInfo
   state: app.models.state.EnvState
-  reward_range: [0.0, 1.0]
+  reward_range: [0.001, 0.999]
   done_type: boolean

pyproject.toml

@@ -23,3 +23,6 @@ build-backend = "setuptools.build_meta"
 [tool.setuptools.packages.find]
 include = ["app*", "server*"]
 exclude = ["data*"]
+
+[tool.pyrefly]
+search_path = ["."]