Update README.md

README.md

@@ -1,66 +1,68 @@
----
-library_name: hivex
-original_train_name: AerialWildfireSuppression_difficulty_4_task_6_run_id_1_train
-tags:
-- hivex
-- hivex-aerial-wildfire-suppression
-- reinforcement-learning
-- multi-agent-reinforcement-learning
-model-index:
-- name: hivex-AWS-PPO-baseline-task-6-difficulty-4
-  results:
-  - task:
-      type: sub-task
-      name: drop_water
-      task-id: 6
-      difficulty-id: 4
-    dataset:
-      name: hivex-aerial-wildfire-suppression
-      type: hivex-aerial-wildfire-suppression
-    metrics:
-    - type: crash_count
-      value: 0.019636338157579303 +/- 0.006296536151540525
-      name: Crash Count
-      verified: true
-    - type: extinguishing_trees
-      value: 0.20098300511017442 +/- 0.20730763026051913
-      name: Extinguishing Trees
-      verified: true
-    - type: extinguishing_trees_reward
-      value: 1.0049150258302688 +/- 1.0365381477211943
-      name: Extinguishing Trees Reward
-      verified: true
-    - type: preparing_trees
-      value: 257.4399574279785 +/- 10.902792920729194
-      name: Preparing Trees
-      verified: true
-    - type: preparing_trees_reward
-      value: 257.4399574279785 +/- 10.902792920729194
-      name: Preparing Trees Reward
-      verified: true
-    - type: water_drop
-      value: 0.9798782348632813 +/- 0.007123928367457922
-      name: Water Drop
-      verified: true
-    - type: water_pickup
-      value: 0.000187265919521451 +/- 0.0008374786518379387
-      name: Water Pickup
-      verified: true
-    - type: cumulative_reward
-      value: 256.58973693847656 +/- 11.54790983559329
-      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>4</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
-
-Environment: **Aerial Wildfire Suppression**<br>
-Task: <code>6</code><br>
-Difficulty: <code>4</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_4_task_6_run_id_1_train
+tags:
+- hivex
+- hivex-aerial-wildfire-suppression
+- reinforcement-learning
+- multi-agent-reinforcement-learning
+model-index:
+- name: hivex-AWS-PPO-baseline-task-6-difficulty-4
+  results:
+  - task:
+      type: sub-task
+      name: drop_water
+      task-id: 6
+      difficulty-id: 4
+    dataset:
+      name: hivex-aerial-wildfire-suppression
+      type: hivex-aerial-wildfire-suppression
+    metrics:
+    - type: crash_count
+      value: 0.019636338157579303 +/- 0.006296536151540525
+      name: Crash Count
+      verified: true
+    - type: extinguishing_trees
+      value: 0.20098300511017442 +/- 0.20730763026051913
+      name: Extinguishing Trees
+      verified: true
+    - type: extinguishing_trees_reward
+      value: 1.0049150258302688 +/- 1.0365381477211943
+      name: Extinguishing Trees Reward
+      verified: true
+    - type: preparing_trees
+      value: 257.4399574279785 +/- 10.902792920729194
+      name: Preparing Trees
+      verified: true
+    - type: preparing_trees_reward
+      value: 257.4399574279785 +/- 10.902792920729194
+      name: Preparing Trees Reward
+      verified: true
+    - type: water_drop
+      value: 0.9798782348632813 +/- 0.007123928367457922
+      name: Water Drop
+      verified: true
+    - type: water_pickup
+      value: 0.000187265919521451 +/- 0.0008374786518379387
+      name: Water Pickup
+      verified: true
+    - type: cumulative_reward
+      value: 256.58973693847656 +/- 11.54790983559329
+      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>4</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
+
+Environment: **Aerial Wildfire Suppression**<br>
+Task: <code>6</code><br>
+Difficulty: <code>4</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