Update README.md

README.md

@@ -1,42 +1,44 @@
----
-library_name: hivex
-original_train_name: AerialWildfireSuppression_difficulty_7_task_5_run_id_2_train
-tags:
-- hivex
-- hivex-aerial-wildfire-suppression
-- reinforcement-learning
-- multi-agent-reinforcement-learning
-model-index:
-- name: hivex-AWS-PPO-baseline-task-5-difficulty-7
-  results:
-  - task:
-      type: sub-task
-      name: pick_up_water
-      task-id: 5
-      difficulty-id: 7
-    dataset:
-      name: hivex-aerial-wildfire-suppression
-      type: hivex-aerial-wildfire-suppression
-    metrics:
-    - type: water_pickup
-      value: 0.9977272719144821 +/- 0.010163948987181867
-      name: Water Pickup
-      verified: true
-    - type: cumulative_reward
-      value: 94.97822952270508 +/- 0.3388395121810205
-      name: Cumulative Reward
-      verified: true
----
-
-This model serves as the baseline for the **Aerial Wildfire Suppression** environment, trained and tested on task <code>5</code> with difficulty <code>7</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
-
-Environment: **Aerial Wildfire Suppression**<br>
-Task: <code>5</code><br>
-Difficulty: <code>7</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_7_task_5_run_id_2_train
+tags:
+- hivex
+- hivex-aerial-wildfire-suppression
+- reinforcement-learning
+- multi-agent-reinforcement-learning
+model-index:
+- name: hivex-AWS-PPO-baseline-task-5-difficulty-7
+  results:
+  - task:
+      type: sub-task
+      name: pick_up_water
+      task-id: 5
+      difficulty-id: 7
+    dataset:
+      name: hivex-aerial-wildfire-suppression
+      type: hivex-aerial-wildfire-suppression
+    metrics:
+    - type: water_pickup
+      value: 0.9977272719144821 +/- 0.010163948987181867
+      name: Water Pickup
+      verified: true
+    - type: cumulative_reward
+      value: 94.97822952270508 +/- 0.3388395121810205
+      name: Cumulative Reward
+      verified: true
+---
+
+This model serves as the baseline for the **Aerial Wildfire Suppression** environment, trained and tested on task <code>5</code> with difficulty <code>7</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
+
+Environment: **Aerial Wildfire Suppression**<br>
+Task: <code>5</code><br>
+Difficulty: <code>7</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