Upload README.md

README.md

@@ -1,60 +1,42 @@
----
-library_name: hivex
-original_train_name: AerialWildfireSuppression_difficulty_5_task_8_run_id_2_train
-tags:
-- hivex
-- hivex-aerial-wildfire-suppression
-- reinforcement-learning
-- multi-agent-reinforcement-learning
-model-index:
-- name: hivex-AWS-PPO-baseline-task-8-difficulty-5
-  results:
-  - task:
-      type: sub-task
-      name: find_village
-      task-id: 8
-    dataset:
-      name: hivex-aerial-wildfire-suppression
-      type: hivex-aerial-wildfire-suppression
-    metrics:
-    - type: cumulative_reward
-      value: 13.988095474243163 +/- 35.57381504941489
-      name: "Cumulative Reward"
-      verified: true
-    - type: crash_count
-      value: 0.07500000223517418 +/- 0.12652577952347
-      name: "Crash Count"
-      verified: true
-    - type: extinguishing_trees
-      value: 0.0 +/- 0.0
-      name: "Extinguishing Trees"
-      verified: true
-    - type: extinguishing_trees_reward
-      value: 0.0 +/- 0.0
-      name: "Extinguishing Trees Reward"
-      verified: true
-    - type: fire_out
-      value: 0.0 +/- 0.0
-      name: "Fire Out"
-      verified: true
-    - type: fire_too_close_to_city
-      value: 0.0 +/- 0.0
-      name: "Fire too Close to City"
-      verified: true
-    - type: preparing_trees
-      value: 0.0 +/- 0.0
-      name: "Preparing Trees"
-      verified: true
-    - type: preparing_trees_reward
-      value: 0.0 +/- 0.0
-      name: "Preparing Trees Reward"
-      verified: true
-    - type: water_drop
-      value: 0.0 +/- 0.0
-      name: "Water Drop"
-      verified: true
-    - type: water_pickup
-      value: 0.0 +/- 0.0
-      name: "Water Pickup"
-      verified: true
----
+---
+library_name: hivex
+original_train_name: AerialWildfireSuppression_difficulty_5_task_8_run_id_2_train
+tags:
+- hivex
+- hivex-aerial-wildfire-suppression
+- reinforcement-learning
+- multi-agent-reinforcement-learning
+model-index:
+- name: hivex-AWS-PPO-baseline-task-8-difficulty-5
+  results:
+  - task:
+      type: sub-task
+      name: find_village
+      task-id: 8
+      difficulty-id: 5
+    dataset:
+      name: hivex-aerial-wildfire-suppression
+      type: hivex-aerial-wildfire-suppression
+    metrics:
+    - type: crash_count
+      value: 0.07500000223517418 +/- 0.12652577952347
+      name: Crash Count
+      verified: true
+    - type: cumulative_reward
+      value: 13.988095474243163 +/- 35.57381504941489
+      name: Cumulative Reward
+      verified: true
+---
+
+This model serves as the baseline for the **Aerial Wildfire Suppression** environment, trained and tested on task <code>8</code> with difficulty <code>5</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
+
+Environment: **Aerial Wildfire Suppression**<br>
+Task: <code>8</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)