Update README.md

README.md

@@ -1,74 +1,76 @@
----
-library_name: hivex
-original_train_name: AerialWildfireSuppression_difficulty_3_task_0_run_id_1_train
-tags:
-- hivex
-- hivex-aerial-wildfire-suppression
-- reinforcement-learning
-- multi-agent-reinforcement-learning
-model-index:
-- name: hivex-AWS-PPO-baseline-task-0-difficulty-3
-  results:
-  - task:
-      type: main-task
-      name: main_task
-      task-id: 0
-      difficulty-id: 3
-    dataset:
-      name: hivex-aerial-wildfire-suppression
-      type: hivex-aerial-wildfire-suppression
-    metrics:
-    - type: crash_count
-      value: 0.0833333358168602 +/- 0.12681432215480823
-      name: Crash Count
-      verified: true
-    - type: extinguishing_trees
-      value: 6.791666813194752 +/- 17.30909921307683
-      name: Extinguishing Trees
-      verified: true
-    - type: extinguishing_trees_reward
-      value: 33.95833272337914 +/- 86.54549141729059
-      name: Extinguishing Trees Reward
-      verified: true
-    - type: fire_out
-      value: 0.3250000037252903 +/- 0.372579912027151
-      name: Fire Out
-      verified: true
-    - type: fire_too_close_to_city
-      value: 0.85 +/- 0.3284733426658932
-      name: Fire too Close to City
-      verified: true
-    - type: preparing_trees
-      value: 1214.2916635513307 +/- 909.8089264585527
-      name: Preparing Trees
-      verified: true
-    - type: preparing_trees_reward
-      value: 1214.2916635513307 +/- 909.8089264585527
-      name: Preparing Trees Reward
-      verified: true
-    - type: water_drop
-      value: 20.291666793823243 +/- 8.402323759531772
-      name: Water Drop
-      verified: true
-    - type: water_pickup
-      value: 19.79166646003723 +/- 8.33067930580936
-      name: Water Pickup
-      verified: true
-    - type: cumulative_reward
-      value: 1321.465838623047 +/- 654.5775149733734
-      name: Cumulative Reward
-      verified: true
----
-
-This model serves as the baseline for the **Aerial Wildfire Suppression** environment, trained and tested on task <code>0</code> with difficulty <code>3</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
-
-Environment: **Aerial Wildfire Suppression**<br>
-Task: <code>0</code><br>
-Difficulty: <code>3</code><br>
-Algorithm: <code>PPO</code><br>
-Episode Length: <code>3000</code><br>
-Training <code>max_steps</code>: <code>1800000</code><br>
-Testing <code>max_steps</code>: <code>180000</code><br><br>
-
-Train & Test [Scripts](https://github.com/hivex-research/hivex)<br>
-Download the [Environment](https://github.com/hivex-research/hivex-environments)
+---
+library_name: hivex
+original_train_name: AerialWildfireSuppression_difficulty_3_task_0_run_id_1_train
+tags:
+- hivex
+- hivex-aerial-wildfire-suppression
+- reinforcement-learning
+- multi-agent-reinforcement-learning
+model-index:
+- name: hivex-AWS-PPO-baseline-task-0-difficulty-3
+  results:
+  - task:
+      type: main-task
+      name: main_task
+      task-id: 0
+      difficulty-id: 3
+    dataset:
+      name: hivex-aerial-wildfire-suppression
+      type: hivex-aerial-wildfire-suppression
+    metrics:
+    - type: crash_count
+      value: 0.0833333358168602 +/- 0.12681432215480823
+      name: Crash Count
+      verified: true
+    - type: extinguishing_trees
+      value: 6.791666813194752 +/- 17.30909921307683
+      name: Extinguishing Trees
+      verified: true
+    - type: extinguishing_trees_reward
+      value: 33.95833272337914 +/- 86.54549141729059
+      name: Extinguishing Trees Reward
+      verified: true
+    - type: fire_out
+      value: 0.3250000037252903 +/- 0.372579912027151
+      name: Fire Out
+      verified: true
+    - type: fire_too_close_to_city
+      value: 0.85 +/- 0.3284733426658932
+      name: Fire too Close to City
+      verified: true
+    - type: preparing_trees
+      value: 1214.2916635513307 +/- 909.8089264585527
+      name: Preparing Trees
+      verified: true
+    - type: preparing_trees_reward
+      value: 1214.2916635513307 +/- 909.8089264585527
+      name: Preparing Trees Reward
+      verified: true
+    - type: water_drop
+      value: 20.291666793823243 +/- 8.402323759531772
+      name: Water Drop
+      verified: true
+    - type: water_pickup
+      value: 19.79166646003723 +/- 8.33067930580936
+      name: Water Pickup
+      verified: true
+    - type: cumulative_reward
+      value: 1321.465838623047 +/- 654.5775149733734
+      name: Cumulative Reward
+      verified: true
+---
+
+This model serves as the baseline for the **Aerial Wildfire Suppression** environment, trained and tested on task <code>0</code> with difficulty <code>3</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
+
+Environment: **Aerial Wildfire Suppression**<br>
+Task: <code>0</code><br>
+Difficulty: <code>3</code><br>
+Algorithm: <code>PPO</code><br>
+Episode Length: <code>3000</code><br>
+Training <code>max_steps</code>: <code>1800000</code><br>
+Testing <code>max_steps</code>: <code>180000</code><br><br>
+
+Train & Test [Scripts](https://github.com/hivex-research/hivex)<br>
+Download the [Environment](https://github.com/hivex-research/hivex-environments)
+
+[hivex-paper]: https://arxiv.org/abs/2501.04180