Upload folder using huggingface_hub

acde_openenv.egg-info/PKG-INFO

@@ -11,6 +11,15 @@ Requires-Dist: requests==2.32.3
 Requires-Dist: openai>=2.7.2
 Requires-Dist: openenv-core
 
+---
+title: ACDE OpenEnv
+emoji: "🚑"
+colorFrom: blue
+colorTo: green
+sdk: docker
+pinned: false
+---
+
 # Emergency Routing Simulation (ACDE)
 
 This project is a simulation environment for emergency ambulance routing.
@@ -95,6 +104,54 @@ When server mode is running:
 - `POST /step`
 - `GET /state`
 
+## Action Space
+
+The agent sends one action per step as JSON:
+
+```json
+{
+  "step": 1,
+  "hospital_id": "H3",
+  "rationale": "short decision reason"
+}
+```
+
+Action fields:
+- `step` (int, >=1): must match current environment step
+- `hospital_id` (str): target hospital identifier
+- `rationale` (str, optional): policy explanation
+
+## Observation Space
+
+Each `reset()` and `step()` returns an observation with:
+- episode metadata: `episode_id`, `seed`, `task_id`, `scenario_name`, `scenario_difficulty`
+- patient state: `patient_condition`, `required_specialization`, remaining time fields
+- hospital list: `hospital_id`, `distance_km`, `icu`, `specialization`, `traffic`
+- routing history: visited/failed hospitals and failure reasons
+- hidden-state feedback: `last_arrival_outcome` summary (status/reason/suitability)
+- memory snapshot used by the baseline policy
+
+Core schema is defined by Pydantic models in:
+- `app/models/action.py`
+- `app/models/observation.py`
+- `app/models/state.py`
+- `app/models/reward.py`
+
+## Required Environment Variables
+
+Before running `inference.py`, define:
+- `API_BASE_URL`: API base URL for the OpenAI-compatible endpoint
+- `MODEL_NAME`: model name used for rationale generation
+- `HF_TOKEN`: API key/token
+
+Windows PowerShell example:
+
+```powershell
+$env:API_BASE_URL = "https://api-inference.huggingface.co/v1"
+$env:MODEL_NAME = "your-model-id"
+$env:HF_TOKEN = "your-token"
+```
+
 ## Installation
 
 ## 1) Prerequisites

app/environment/core.py

@@ -1,4 +1,4 @@
-import json
+import json
 from pathlib import Path
 from typing import Any, Literal, cast
 
@@ -681,7 +681,7 @@ class EmergencyEnv:
             status="rejected",
             reason="Hidden mismatch at arrival (wrong risky guess). Rerouting required.",
             validation_details=arrival_outcome.validation_details,
-            reward_modifier=0.0,
+            reward_modifier=0.001,
         )
         return (
             forced_reject,
@@ -759,7 +759,7 @@ class EmergencyEnv:
                 status="rejected",
                 reason=reason,
                 validation_details=new_validation,
-                reward_modifier=0.0,
+                reward_modifier=0.001,
             ),
             0.12,
             f"Hidden case: {reason}. Rerouting required.",
@@ -810,7 +810,7 @@ class EmergencyEnv:
                 status="rejected",
                 reason="Condition became irreversible after delays",
                 validation_details=arrival_outcome.validation_details,
-                reward_modifier=0.0,
+                reward_modifier=0.001,
             ),
             "Partial chain cap: condition became irreversible.",
         )
@@ -888,7 +888,7 @@ class EmergencyEnv:
                     status="rejected",
                     reason="Condition relapsed after temporary stabilization",
                     validation_details=arrival_outcome.validation_details,
-                    reward_modifier=0.0,
+                    reward_modifier=0.001,
                     terminal=False,
                 ),
                 "Recovery guard: partial relapsed to rejected.",
@@ -967,7 +967,7 @@ class EmergencyEnv:
                 "dynamic_delay": dynamic_delay,
                 "critical_limit": self.state_data.critical_time_limit_minutes,
                 "specialization_match": self._specialization_match(selected),
-                "suitability_score": arrival_outcome.validation_details.patient_suitability if arrival_outcome.validation_details else 0.5,
+                "suitability_score": max(MIN_REWARD, min(MAX_REWARD, arrival_outcome.validation_details.patient_suitability if arrival_outcome.validation_details else 0.5)),
             }
         )
 

app/environment/validation.py

@@ -192,9 +192,10 @@ class HospitalValidator:
         # Add difficulty-based noise
         if difficulty == "hard":
             noise = self.rng.uniform(-0.15, 0.15)
-            suitability = max(0.0, min(1.0, suitability + noise))
+            suitability = suitability + noise
         
-        return suitability
+        # Clamp to strict (0, 1) — validator rejects exact 0.0 and 1.0
+        return max(0.001, min(0.999, suitability))
 
     def _determine_outcome(
         self,
@@ -271,7 +272,7 @@ class HospitalValidator:
             return (
                 "rejected",
                 f"Hospital cannot admit: {', '.join(rejection_reasons[:2])}",
-                0.0,
+                0.001,
                 False,
             )
         
@@ -347,7 +348,7 @@ class HospitalValidator:
                 return (
                     "rejected",
                     "Condition became non-transferable during delay; immediate critical care failed",
-                    0.0,
+                    0.001,
                     True,
                 )
 
@@ -359,7 +360,7 @@ class HospitalValidator:
             )
         
         # Full acceptance
-        confidence_bonus = 1.0
+        confidence_bonus = 0.999
         if validation.patient_suitability >= 0.8:
             confidence_bonus = 1.1
         elif validation.patient_suitability >= 0.7:
@@ -378,7 +379,7 @@ class HospitalValidator:
             return (
                 "rejected",
                 "Unexpected complication at arrival",
-                0.0,
+                0.001,
                 False,
             )
 
@@ -386,7 +387,7 @@ class HospitalValidator:
             return (
                 "accepted",
                 "successful admission under uncertainty",
-                1.0,
+                0.999,
                 False,
             )