Update README.md

README.md

@@ -1,74 +1,76 @@
----
-library_name: hivex
-original_train_name: AerialWildfireSuppression_difficulty_8_task_4_run_id_0_train
-tags:
-- hivex
-- hivex-aerial-wildfire-suppression
-- reinforcement-learning
-- multi-agent-reinforcement-learning
-model-index:
-- name: hivex-AWS-PPO-baseline-task-4-difficulty-8
-  results:
-  - task:
-      type: sub-task
-      name: protect_village
-      task-id: 4
-      difficulty-id: 8
-    dataset:
-      name: hivex-aerial-wildfire-suppression
-      type: hivex-aerial-wildfire-suppression
-    metrics:
-    - type: crash_count
-      value: 0.9925824165344238 +/- 0.02284823226393604
-      name: Crash Count
-      verified: true
-    - type: extinguishing_trees
-      value: 0.0949134185910225 +/- 0.27686598704684745
-      name: Extinguishing Trees
-      verified: true
-    - type: extinguishing_trees_reward
-      value: 0.4745671033859253 +/- 1.3843300000675678
-      name: Extinguishing Trees Reward
-      verified: true
-    - type: fire_out
-      value: 0.00357142873108387 +/- 0.015971914838998697
-      name: Fire Out
-      verified: true
-    - type: fire_too_close_to_city
-      value: 0.026685259863734247 +/- 0.042508034690655574
-      name: Fire too Close to City
-      verified: true
-    - type: preparing_trees
-      value: 281.05667572021486 +/- 33.36053303432415
-      name: Preparing Trees
-      verified: true
-    - type: preparing_trees_reward
-      value: 281.05667572021486 +/- 33.36053303432415
-      name: Preparing Trees Reward
-      verified: true
-    - type: water_drop
-      value: 1.9489688873291016 +/- 0.2672890550666218
-      name: Water Drop
-      verified: true
-    - type: water_pickup
-      value: 1.9453974604606628 +/- 0.2713707685551629
-      name: Water Pickup
-      verified: true
-    - type: cumulative_reward
-      value: 171.03001670837403 +/- 35.59643888706601
-      name: Cumulative Reward
-      verified: true
----
-
-This model serves as the baseline for the **Aerial Wildfire Suppression** environment, trained and tested on task <code>4</code> with difficulty <code>8</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
-
-Environment: **Aerial Wildfire Suppression**<br>
-Task: <code>4</code><br>
-Difficulty: <code>8</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_8_task_4_run_id_0_train
+tags:
+- hivex
+- hivex-aerial-wildfire-suppression
+- reinforcement-learning
+- multi-agent-reinforcement-learning
+model-index:
+- name: hivex-AWS-PPO-baseline-task-4-difficulty-8
+  results:
+  - task:
+      type: sub-task
+      name: protect_village
+      task-id: 4
+      difficulty-id: 8
+    dataset:
+      name: hivex-aerial-wildfire-suppression
+      type: hivex-aerial-wildfire-suppression
+    metrics:
+    - type: crash_count
+      value: 0.9925824165344238 +/- 0.02284823226393604
+      name: Crash Count
+      verified: true
+    - type: extinguishing_trees
+      value: 0.0949134185910225 +/- 0.27686598704684745
+      name: Extinguishing Trees
+      verified: true
+    - type: extinguishing_trees_reward
+      value: 0.4745671033859253 +/- 1.3843300000675678
+      name: Extinguishing Trees Reward
+      verified: true
+    - type: fire_out
+      value: 0.00357142873108387 +/- 0.015971914838998697
+      name: Fire Out
+      verified: true
+    - type: fire_too_close_to_city
+      value: 0.026685259863734247 +/- 0.042508034690655574
+      name: Fire too Close to City
+      verified: true
+    - type: preparing_trees
+      value: 281.05667572021486 +/- 33.36053303432415
+      name: Preparing Trees
+      verified: true
+    - type: preparing_trees_reward
+      value: 281.05667572021486 +/- 33.36053303432415
+      name: Preparing Trees Reward
+      verified: true
+    - type: water_drop
+      value: 1.9489688873291016 +/- 0.2672890550666218
+      name: Water Drop
+      verified: true
+    - type: water_pickup
+      value: 1.9453974604606628 +/- 0.2713707685551629
+      name: Water Pickup
+      verified: true
+    - type: cumulative_reward
+      value: 171.03001670837403 +/- 35.59643888706601
+      name: Cumulative Reward
+      verified: true
+---
+
+This model serves as the baseline for the **Aerial Wildfire Suppression** environment, trained and tested on task <code>4</code> with difficulty <code>8</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
+
+Environment: **Aerial Wildfire Suppression**<br>
+Task: <code>4</code><br>
+Difficulty: <code>8</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