Spaces:

Draken1606
/

Container-Port

Sleeping

Draken1606 commited on 30 days ago

Commit

6f90d54

1 Parent(s): 16229c6

fix: ensure task scores are strictly between 0 and 1 (exclusive)

- Update score() method in server/environment.py to return values in (0.01, 0.99) range
- Change default score from 0.0 to 0.5 in models.py
- Clean up inference.py environment variable handling per hackathon guidelines
- Initialize OpenAI client at module level with proper error checking

Files changed (5) hide show

README.md +2 -0
inference.py +9 -10
models.py +1 -1
server/app.py +166 -0
server/environment.py +4 -4

README.md CHANGED Viewed

@@ -37,6 +37,8 @@ uvicorn server.app:app --host 0.0.0.0 --port 7860
 Web UI: `http://127.0.0.1:7860/web`
 For manual stateful checks, use the web endpoints:
 ```bash

 Web UI: `http://127.0.0.1:7860/web`
+Interactive dashboard with difficulty dropdown: `http://127.0.0.1:7860/dashboard`
 For manual stateful checks, use the web endpoints:
 ```bash

inference.py CHANGED Viewed

@@ -43,16 +43,16 @@ def _load_dotenv() -> None:
 _load_dotenv()
 HF_TOKEN = os.getenv('HF_TOKEN')
 API_BASE_URL = os.getenv('API_BASE_URL', 'https://api.openai.com/v1')
 MODEL_NAME = os.getenv('MODEL_NAME', 'meta-llama/Llama-3.1-8B-Instruct')
-LOCAL_IMAGE_NAME = os.getenv('LOCAL_IMAGE_NAME')
-OPENAI_API_KEY = HF_TOKENAPI_KEY = os.getenv('API_KEY')
-API_KEY = HF_TOKEN
-AUTH_TOKEN =  HF_TOKEN or API_KEY or OPENAI_API_KEY
-if AUTH_TOKEN is None:
-    raise ValueError('OPENAI_API_KEY (or API_KEY/HF_TOKEN) environment variable is required')
 ENV_URL = os.getenv('ENV_URL', 'http://localhost:7860')
 TASK_NAME = 'container-stacking'
@@ -188,7 +188,7 @@ async def run_episode(url: str, difficulty: str = 'medium', use_llm: bool = Fals
     if not ws_url.endswith('/ws'):
         ws_url = ws_url.rstrip('/') + '/ws'
-    client = OpenAI(base_url=API_BASE_URL, api_key=AUTH_TOKEN) if use_llm else None
     model_label = MODEL_NAME if use_llm else 'greedy'
     log_start(task=f'{TASK_NAME}-{difficulty}', env=BENCHMARK, model=model_label)
@@ -209,7 +209,7 @@ async def run_episode(url: str, difficulty: str = 'medium', use_llm: bool = Fals
                 if obs.get('done', False):
                     break
-                action_idx = llm_decide(obs, client) if use_llm else greedy_decide(obs)
                 await ws.send(json.dumps({'type': 'step', 'data': {'stack_index': action_idx}}))
                 resp = json.loads(await ws.recv())
@@ -229,8 +229,7 @@ async def run_episode(url: str, difficulty: str = 'medium', use_llm: bool = Fals
             await ws.send(json.dumps({'type': 'state'}))
             state_resp = json.loads(await ws.recv())
             state = state_resp.get('data', {})
-            score = float(state.get('score', obs.get('score', 0.0)))
-            score = min(max(score, 0.0), 1.0)
         success = score >= SUCCESS_SCORE_THRESHOLD

 _load_dotenv()
+# Required environment variables
 HF_TOKEN = os.getenv('HF_TOKEN')
 API_BASE_URL = os.getenv('API_BASE_URL', 'https://api.openai.com/v1')
 MODEL_NAME = os.getenv('MODEL_NAME', 'meta-llama/Llama-3.1-8B-Instruct')
+if HF_TOKEN is None:
+    raise ValueError('HF_TOKEN environment variable is required')
+# Initialize OpenAI client
+client = OpenAI(base_url=API_BASE_URL, api_key=HF_TOKEN)
 ENV_URL = os.getenv('ENV_URL', 'http://localhost:7860')
 TASK_NAME = 'container-stacking'
     if not ws_url.endswith('/ws'):
         ws_url = ws_url.rstrip('/') + '/ws'
+    llm_client = client if use_llm else None
     model_label = MODEL_NAME if use_llm else 'greedy'
     log_start(task=f'{TASK_NAME}-{difficulty}', env=BENCHMARK, model=model_label)
                 if obs.get('done', False):
                     break
+                action_idx = llm_decide(obs, llm_client) if use_llm else greedy_decide(obs)
                 await ws.send(json.dumps({'type': 'step', 'data': {'stack_index': action_idx}}))
                 resp = json.loads(await ws.recv())
             await ws.send(json.dumps({'type': 'state'}))
             state_resp = json.loads(await ws.recv())
             state = state_resp.get('data', {})
+            score = float(state.get('score', obs.get('score', 0.5)))
         success = score >= SUCCESS_SCORE_THRESHOLD

models.py CHANGED Viewed

@@ -36,5 +36,5 @@ class ContainerObservation(Observation):
     max_height: int = Field(0)
     difficulty: str = Field("medium")
     last_reward: float = Field(0.0)
-    score: float = Field(0.0, description="Normalized score 0.0-1.0")
     done: bool = Field(False)

     max_height: int = Field(0)
     difficulty: str = Field("medium")
     last_reward: float = Field(0.0)
+    score: float = Field(0.5, description="Normalized score (0.0, 1.0)")
     done: bool = Field(False)

server/app.py CHANGED Viewed

@@ -15,6 +15,7 @@ if str(PROJECT_ROOT) not in sys.path:
 os.environ.setdefault("ENABLE_WEB_INTERFACE", "true")
 from openenv.core.env_server import create_web_interface_app
 import uvicorn
 from models import ContainerAction, ContainerObservation
@@ -28,6 +29,171 @@ app = create_web_interface_app(
 )
 def main() -> None:
     uvicorn.run("server.app:app", host="0.0.0.0", port=7860)

 os.environ.setdefault("ENABLE_WEB_INTERFACE", "true")
 from openenv.core.env_server import create_web_interface_app
+from fastapi.responses import HTMLResponse
 import uvicorn
 from models import ContainerAction, ContainerObservation
 )
+@app.get("/dashboard", response_class=HTMLResponse)
+def dashboard() -> str:
+        return """
+<!doctype html>
+<html lang="en">
+<head>
+    <meta charset="utf-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1" />
+    <title>Container Port Dashboard</title>
+    <style>
+        :root {
+            --bg: #f4f5ef;
+            --card: #ffffff;
+            --ink: #18211f;
+            --accent: #0b6e4f;
+            --muted: #5f6a66;
+            --line: #d7ddd7;
+        }
+        * { box-sizing: border-box; }
+        body {
+            margin: 0;
+            padding: 24px;
+            background: radial-gradient(circle at 80% 20%, #dbeee5 0, var(--bg) 45%);
+            color: var(--ink);
+            font-family: "Segoe UI", Tahoma, Geneva, Verdana, sans-serif;
+        }
+        .wrap { max-width: 980px; margin: 0 auto; }
+        h1 { margin: 0 0 8px; }
+        p { margin: 0 0 16px; color: var(--muted); }
+        .panel {
+            background: var(--card);
+            border: 1px solid var(--line);
+            border-radius: 14px;
+            padding: 16px;
+            margin-bottom: 16px;
+        }
+        .row {
+            display: flex;
+            gap: 10px;
+            flex-wrap: wrap;
+            align-items: center;
+        }
+        select, input, button {
+            border: 1px solid var(--line);
+            border-radius: 10px;
+            padding: 10px 12px;
+            font-size: 14px;
+            background: #fff;
+            color: var(--ink);
+        }
+        button {
+            cursor: pointer;
+            background: var(--accent);
+            color: #fff;
+            border-color: var(--accent);
+            font-weight: 600;
+        }
+        button.secondary {
+            background: #fff;
+            color: var(--ink);
+            border-color: var(--line);
+            font-weight: 500;
+        }
+        pre {
+            margin: 0;
+            background: #0e1a17;
+            color: #eaf8f1;
+            border-radius: 12px;
+            padding: 14px;
+            overflow: auto;
+            min-height: 220px;
+            font-size: 12px;
+            line-height: 1.35;
+        }
+        .hint { font-size: 12px; color: var(--muted); margin-top: 8px; }
+    </style>
+</head>
+<body>
+    <div class="wrap">
+        <h1>Container Port Dashboard</h1>
+        <p>Pick a difficulty and step the environment manually.</p>
+        <div class="panel">
+            <div class="row">
+                <label for="difficulty">Difficulty</label>
+                <select id="difficulty">
+                    <option value="easy">Easy</option>
+                    <option value="medium" selected>Medium</option>
+                    <option value="hard">Hard</option>
+                </select>
+                <button id="resetBtn">Reset</button>
+                <button id="stateBtn" class="secondary">State</button>
+            </div>
+            <div class="hint">Reset calls <code>/web/reset</code> with the selected mode.</div>
+        </div>
+        <div class="panel">
+            <div class="row">
+                <label for="stack">stack_index</label>
+                <input id="stack" type="number" min="0" step="1" value="0" />
+                <button id="stepBtn">Step</button>
+            </div>
+            <div class="hint">Step calls <code>/web/step</code> with action <code>{"stack_index": n}</code>.</div>
+        </div>
+        <div class="panel">
+            <pre id="out">Click Reset to start an episode.</pre>
+        </div>
+    </div>
+    <script>
+        const out = document.getElementById('out');
+        const difficulty = document.getElementById('difficulty');
+        const stack = document.getElementById('stack');
+        function show(data) {
+            out.textContent = JSON.stringify(data, null, 2);
+        }
+        async function postJson(url, payload) {
+            const res = await fetch(url, {
+                method: 'POST',
+                headers: { 'Content-Type': 'application/json' },
+                body: JSON.stringify(payload),
+            });
+            const data = await res.json();
+            show(data);
+        }
+        async function getJson(url) {
+            const res = await fetch(url);
+            const data = await res.json();
+            show(data);
+        }
+        document.getElementById('resetBtn').addEventListener('click', async () => {
+            try {
+                await postJson('/web/reset', { difficulty: difficulty.value });
+            } catch (err) {
+                show({ error: String(err) });
+            }
+        });
+        document.getElementById('stepBtn').addEventListener('click', async () => {
+            const idx = Number(stack.value);
+            try {
+                await postJson('/web/step', { action: { stack_index: idx } });
+            } catch (err) {
+                show({ error: String(err) });
+            }
+        });
+        document.getElementById('stateBtn').addEventListener('click', async () => {
+            try {
+                await getJson('/web/state');
+            } catch (err) {
+                show({ error: String(err) });
+            }
+        });
+    </script>
+</body>
+</html>
+"""
 def main() -> None:
     uvicorn.run("server.app:app", host="0.0.0.0", port=7860)

server/environment.py CHANGED Viewed

@@ -229,13 +229,13 @@ class ContainerYardEnvironment(Environment):
         )
     def score(self) -> float:
-        """Normalized score in [0.0, 1.0]. Based on actual retrievals attempted."""
         n_retrieved = self.retrieval_pointer  # only count retrievals that actually happened
         worst_case = n_retrieved * (self.max_height - 1)
         if worst_case == 0:
-            return 1.0
-        score = max(0.0, 1.0 - self.rehandle_count / worst_case)
-        return round(min(score, 1.0), 4)
     def get_state(self) -> dict[str, Any]:
         return self._observe().model_dump()

         )
     def score(self) -> float:
+        """Normalized score in (0.0, 1.0). Based on actual retrievals attempted."""
         n_retrieved = self.retrieval_pointer  # only count retrievals that actually happened
         worst_case = n_retrieved * (self.max_height - 1)
         if worst_case == 0:
+            return 0.99
+        score = max(0.01, min(1.0 - self.rehandle_count / worst_case, 0.99))
+        return round(score, 4)
     def get_state(self) -> dict[str, Any]:
         return self._observe().model_dump()