Publish independent 20-episode Unity evaluation

README.md

@@ -5,8 +5,22 @@ tags:
 - deep-reinforcement-learning
 - reinforcement-learning
 - ML-Agents-Pyramids
+model-index:
+- name: ppo-Pyramids
+  results:
+  - task:
+      type: reinforcement-learning
+      name: Reinforcement Learning
+    dataset:
+      name: ML-Agents-Pyramids
+      type: ML-Agents-Pyramids
+    metrics:
+    - type: mean_reward
+      name: mean_reward
+      value: 1.77 +/- 0.11
 ---
 
+
   # **ppo** Agent playing **Pyramids**
   This is a trained model of a **ppo** agent playing **Pyramids**
   using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
@@ -32,4 +46,5 @@ tags:
   2. Step 1: Find your model_id: jos0054/ppo-Pyramids
   3. Step 2: Select your *.nn /*.onnx file
   4. Click on Watch the agent play 👀
-  
+  
+Independent ONNX inference evaluation: 1.77 +/- 0.11, 20 completed episodes, seed 31415. Mean minus standard deviation: 1.66.

results.json

@@ -0,0 +1,30 @@
+{
+  "env_id": "ML-Agents-Pyramids",
+  "mean_reward": 1.7673700160288717,
+  "std_reward": 0.10852730290590747,
+  "course_score": 1.6588427131229642,
+  "n_evaluation_episodes": 20,
+  "seed": 31415,
+  "episode_returns": [
+    1.9030000066850334,
+    1.899000006960705,
+    1.8820000081323087,
+    1.8570000098552555,
+    1.8290000117849559,
+    1.8090000131633133,
+    1.7960000140592456,
+    1.7810000150930136,
+    1.745000017574057,
+    1.8722000087727793,
+    1.7270000188145787,
+    1.7030000204686075,
+    1.6720000226050615,
+    1.6400000248104334,
+    1.8030000135768205,
+    1.715000019641593,
+    1.84500001068227,
+    1.5770000291522592,
+    1.8102000130456872,
+    1.482000035699457
+  ]
+}