Update README.md

README.md

@@ -1,62 +1,64 @@
----
-library_name: hivex
-original_train_name: AerialWildfireSuppression_difficulty_2_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-2
-  results:
-  - task:
-      type: sub-task
-      name: drop_water
-      task-id: 6
-      difficulty-id: 2
-    dataset:
-      name: hivex-aerial-wildfire-suppression
-      type: hivex-aerial-wildfire-suppression
-    metrics:
-    - type: crash_count
-      value: 0.029796552332118153 +/- 0.013558095195825941
-      name: Crash Count
-      verified: true
-    - type: extinguishing_trees
-      value: 0.3805455264635384 +/- 0.49240092917648515
-      name: Extinguishing Trees
-      verified: true
-    - type: extinguishing_trees_reward
-      value: 1.9027276199311018 +/- 2.462004661948154
-      name: Extinguishing Trees Reward
-      verified: true
-    - type: preparing_trees
-      value: 182.82622451782225 +/- 11.38041138346274
-      name: Preparing Trees
-      verified: true
-    - type: preparing_trees_reward
-      value: 182.82622451782225 +/- 11.38041138346274
-      name: Preparing Trees Reward
-      verified: true
-    - type: water_drop
-      value: 0.9693701088428497 +/- 0.015894927913693367
-      name: Water Drop
-      verified: true
-    - type: cumulative_reward
-      value: 181.8419204711914 +/- 12.238550390744056
-      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>2</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
-
-Environment: **Aerial Wildfire Suppression**<br>
-Task: <code>6</code><br>
-Difficulty: <code>2</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_2_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-2
+  results:
+  - task:
+      type: sub-task
+      name: drop_water
+      task-id: 6
+      difficulty-id: 2
+    dataset:
+      name: hivex-aerial-wildfire-suppression
+      type: hivex-aerial-wildfire-suppression
+    metrics:
+    - type: crash_count
+      value: 0.029796552332118153 +/- 0.013558095195825941
+      name: Crash Count
+      verified: true
+    - type: extinguishing_trees
+      value: 0.3805455264635384 +/- 0.49240092917648515
+      name: Extinguishing Trees
+      verified: true
+    - type: extinguishing_trees_reward
+      value: 1.9027276199311018 +/- 2.462004661948154
+      name: Extinguishing Trees Reward
+      verified: true
+    - type: preparing_trees
+      value: 182.82622451782225 +/- 11.38041138346274
+      name: Preparing Trees
+      verified: true
+    - type: preparing_trees_reward
+      value: 182.82622451782225 +/- 11.38041138346274
+      name: Preparing Trees Reward
+      verified: true
+    - type: water_drop
+      value: 0.9693701088428497 +/- 0.015894927913693367
+      name: Water Drop
+      verified: true
+    - type: cumulative_reward
+      value: 181.8419204711914 +/- 12.238550390744056
+      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>2</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
+
+Environment: **Aerial Wildfire Suppression**<br>
+Task: <code>6</code><br>
+Difficulty: <code>2</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