Update README.md

README.md

@@ -1,74 +1,76 @@
----
-library_name: hivex
-original_train_name: AerialWildfireSuppression_difficulty_8_task_0_run_id_2_train
-tags:
-- hivex
-- hivex-aerial-wildfire-suppression
-- reinforcement-learning
-- multi-agent-reinforcement-learning
-model-index:
-- name: hivex-AWS-PPO-baseline-task-0-difficulty-8
-  results:
-  - task:
-      type: main-task
-      name: main_task
-      task-id: 0
-      difficulty-id: 8
-    dataset:
-      name: hivex-aerial-wildfire-suppression
-      type: hivex-aerial-wildfire-suppression
-    metrics:
-    - type: crash_count
-      value: 0.10833333656191826 +/- 0.14584900099920892
-      name: Crash Count
-      verified: true
-    - type: extinguishing_trees
-      value: 23.324999898672104 +/- 55.08031019150775
-      name: Extinguishing Trees
-      verified: true
-    - type: extinguishing_trees_reward
-      value: 116.62500007152558 +/- 275.40155086604756
-      name: Extinguishing Trees Reward
-      verified: true
-    - type: fire_out
-      value: 0.22500000149011612 +/- 0.3638448035924671
-      name: Fire Out
-      verified: true
-    - type: fire_too_close_to_city
-      value: 0.85 +/- 0.28562028528873973
-      name: Fire too Close to City
-      verified: true
-    - type: preparing_trees
-      value: 769.4333295822144 +/- 713.797537109146
-      name: Preparing Trees
-      verified: true
-    - type: preparing_trees_reward
-      value: 769.4333295822144 +/- 713.797537109146
-      name: Preparing Trees Reward
-      verified: true
-    - type: water_drop
-      value: 42.46666691303253 +/- 16.681099284118027
-      name: Water Drop
-      verified: true
-    - type: water_pickup
-      value: 42.0666668176651 +/- 16.62014604652166
-      name: Water Pickup
-      verified: true
-    - type: cumulative_reward
-      value: 1093.1966667175293 +/- 733.5777441210589
-      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>8</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
-
-Environment: **Aerial Wildfire Suppression**<br>
-Task: <code>0</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_0_run_id_2_train
+tags:
+- hivex
+- hivex-aerial-wildfire-suppression
+- reinforcement-learning
+- multi-agent-reinforcement-learning
+model-index:
+- name: hivex-AWS-PPO-baseline-task-0-difficulty-8
+  results:
+  - task:
+      type: main-task
+      name: main_task
+      task-id: 0
+      difficulty-id: 8
+    dataset:
+      name: hivex-aerial-wildfire-suppression
+      type: hivex-aerial-wildfire-suppression
+    metrics:
+    - type: crash_count
+      value: 0.10833333656191826 +/- 0.14584900099920892
+      name: Crash Count
+      verified: true
+    - type: extinguishing_trees
+      value: 23.324999898672104 +/- 55.08031019150775
+      name: Extinguishing Trees
+      verified: true
+    - type: extinguishing_trees_reward
+      value: 116.62500007152558 +/- 275.40155086604756
+      name: Extinguishing Trees Reward
+      verified: true
+    - type: fire_out
+      value: 0.22500000149011612 +/- 0.3638448035924671
+      name: Fire Out
+      verified: true
+    - type: fire_too_close_to_city
+      value: 0.85 +/- 0.28562028528873973
+      name: Fire too Close to City
+      verified: true
+    - type: preparing_trees
+      value: 769.4333295822144 +/- 713.797537109146
+      name: Preparing Trees
+      verified: true
+    - type: preparing_trees_reward
+      value: 769.4333295822144 +/- 713.797537109146
+      name: Preparing Trees Reward
+      verified: true
+    - type: water_drop
+      value: 42.46666691303253 +/- 16.681099284118027
+      name: Water Drop
+      verified: true
+    - type: water_pickup
+      value: 42.0666668176651 +/- 16.62014604652166
+      name: Water Pickup
+      verified: true
+    - type: cumulative_reward
+      value: 1093.1966667175293 +/- 733.5777441210589
+      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>8</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
+
+Environment: **Aerial Wildfire Suppression**<br>
+Task: <code>0</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