Update README.md

README.md

@@ -1,66 +1,68 @@
----
-library_name: hivex
-original_train_name: AerialWildfireSuppression_difficulty_5_task_6_run_id_2_train
-tags:
-- hivex
-- hivex-aerial-wildfire-suppression
-- reinforcement-learning
-- multi-agent-reinforcement-learning
-model-index:
-- name: hivex-AWS-PPO-baseline-task-6-difficulty-5
-  results:
-  - task:
-      type: sub-task
-      name: drop_water
-      task-id: 6
-      difficulty-id: 5
-    dataset:
-      name: hivex-aerial-wildfire-suppression
-      type: hivex-aerial-wildfire-suppression
-    metrics:
-    - type: crash_count
-      value: 0.022751575300935654 +/- 0.009602885208751202
-      name: Crash Count
-      verified: true
-    - type: extinguishing_trees
-      value: 0.2077373639680445 +/- 0.1507774190085061
-      name: Extinguishing Trees
-      verified: true
-    - type: extinguishing_trees_reward
-      value: 1.0386868014931678 +/- 0.753887068245034
-      name: Extinguishing Trees Reward
-      verified: true
-    - type: preparing_trees
-      value: 275.6179458618164 +/- 12.486733727275665
-      name: Preparing Trees
-      verified: true
-    - type: preparing_trees_reward
-      value: 275.6179458618164 +/- 12.486733727275665
-      name: Preparing Trees Reward
-      verified: true
-    - type: water_drop
-      value: 0.9767484277486801 +/- 0.00989079886411895
-      name: Water Drop
-      verified: true
-    - type: water_pickup
-      value: 0.0005922459880821407 +/- 0.0015700193469281448
-      name: Water Pickup
-      verified: true
-    - type: cumulative_reward
-      value: 274.48731155395507 +/- 13.254462171454286
-      name: Cumulative Reward
-      verified: true
----
-
-This model serves as the baseline for the **Aerial Wildfire Suppression** environment, trained and tested on task <code>6</code> with difficulty <code>5</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
-
-Environment: **Aerial Wildfire Suppression**<br>
-Task: <code>6</code><br>
-Difficulty: <code>5</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_5_task_6_run_id_2_train
+tags:
+- hivex
+- hivex-aerial-wildfire-suppression
+- reinforcement-learning
+- multi-agent-reinforcement-learning
+model-index:
+- name: hivex-AWS-PPO-baseline-task-6-difficulty-5
+  results:
+  - task:
+      type: sub-task
+      name: drop_water
+      task-id: 6
+      difficulty-id: 5
+    dataset:
+      name: hivex-aerial-wildfire-suppression
+      type: hivex-aerial-wildfire-suppression
+    metrics:
+    - type: crash_count
+      value: 0.022751575300935654 +/- 0.009602885208751202
+      name: Crash Count
+      verified: true
+    - type: extinguishing_trees
+      value: 0.2077373639680445 +/- 0.1507774190085061
+      name: Extinguishing Trees
+      verified: true
+    - type: extinguishing_trees_reward
+      value: 1.0386868014931678 +/- 0.753887068245034
+      name: Extinguishing Trees Reward
+      verified: true
+    - type: preparing_trees
+      value: 275.6179458618164 +/- 12.486733727275665
+      name: Preparing Trees
+      verified: true
+    - type: preparing_trees_reward
+      value: 275.6179458618164 +/- 12.486733727275665
+      name: Preparing Trees Reward
+      verified: true
+    - type: water_drop
+      value: 0.9767484277486801 +/- 0.00989079886411895
+      name: Water Drop
+      verified: true
+    - type: water_pickup
+      value: 0.0005922459880821407 +/- 0.0015700193469281448
+      name: Water Pickup
+      verified: true
+    - type: cumulative_reward
+      value: 274.48731155395507 +/- 13.254462171454286
+      name: Cumulative Reward
+      verified: true
+---
+
+This model serves as the baseline for the **Aerial Wildfire Suppression** environment, trained and tested on task <code>6</code> with difficulty <code>5</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
+
+Environment: **Aerial Wildfire Suppression**<br>
+Task: <code>6</code><br>
+Difficulty: <code>5</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