Update README.md

README.md

@@ -1,66 +1,68 @@
----
-library_name: hivex
-original_train_name: AerialWildfireSuppression_difficulty_3_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-3
-  results:
-  - task:
-      type: sub-task
-      name: drop_water
-      task-id: 6
-      difficulty-id: 3
-    dataset:
-      name: hivex-aerial-wildfire-suppression
-      type: hivex-aerial-wildfire-suppression
-    metrics:
-    - type: crash_count
-      value: 0.01590130275581032 +/- 0.009051027459662414
-      name: Crash Count
-      verified: true
-    - type: extinguishing_trees
-      value: 0.2118260153569281 +/- 0.3283880873127659
-      name: Extinguishing Trees
-      verified: true
-    - type: extinguishing_trees_reward
-      value: 1.0591301042586565 +/- 1.641940515491148
-      name: Extinguishing Trees Reward
-      verified: true
-    - type: preparing_trees
-      value: 234.83799896240234 +/- 10.68919451687246
-      name: Preparing Trees
-      verified: true
-    - type: preparing_trees_reward
-      value: 234.83799896240234 +/- 10.68919451687246
-      name: Preparing Trees Reward
-      verified: true
-    - type: water_drop
-      value: 0.9835368990898132 +/- 0.009798197368354513
-      name: Water Drop
-      verified: true
-    - type: water_pickup
-      value: 0.000875470065511763 +/- 0.001850762177686202
-      name: Water Pickup
-      verified: true
-    - type: cumulative_reward
-      value: 234.31187438964844 +/- 9.555234680707661
-      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>3</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
-
-Environment: **Aerial Wildfire Suppression**<br>
-Task: <code>6</code><br>
-Difficulty: <code>3</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_3_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-3
+  results:
+  - task:
+      type: sub-task
+      name: drop_water
+      task-id: 6
+      difficulty-id: 3
+    dataset:
+      name: hivex-aerial-wildfire-suppression
+      type: hivex-aerial-wildfire-suppression
+    metrics:
+    - type: crash_count
+      value: 0.01590130275581032 +/- 0.009051027459662414
+      name: Crash Count
+      verified: true
+    - type: extinguishing_trees
+      value: 0.2118260153569281 +/- 0.3283880873127659
+      name: Extinguishing Trees
+      verified: true
+    - type: extinguishing_trees_reward
+      value: 1.0591301042586565 +/- 1.641940515491148
+      name: Extinguishing Trees Reward
+      verified: true
+    - type: preparing_trees
+      value: 234.83799896240234 +/- 10.68919451687246
+      name: Preparing Trees
+      verified: true
+    - type: preparing_trees_reward
+      value: 234.83799896240234 +/- 10.68919451687246
+      name: Preparing Trees Reward
+      verified: true
+    - type: water_drop
+      value: 0.9835368990898132 +/- 0.009798197368354513
+      name: Water Drop
+      verified: true
+    - type: water_pickup
+      value: 0.000875470065511763 +/- 0.001850762177686202
+      name: Water Pickup
+      verified: true
+    - type: cumulative_reward
+      value: 234.31187438964844 +/- 9.555234680707661
+      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>3</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
+
+Environment: **Aerial Wildfire Suppression**<br>
+Task: <code>6</code><br>
+Difficulty: <code>3</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