Update README.md

README.md

@@ -1,41 +1,54 @@
----
-library_name: hivex
-original_train_name: WildfireResourceManagement_difficulty_4_task_2_run_id_0_train
-tags:
-- hivex
-- hivex-wildfire-resource-management
-- reinforcement-learning
-- multi-agent-reinforcement-learning
-model-index:
-- name: hivex-WRM-PPO-baseline-task-2-difficulty-4
-  results:
-  - task:
-      type: sub-task
-      name: distribute_all
-      task-id: 2
-      difficulty-id: 4
-    dataset:
-      name: hivex-wildfire-resource-management
-      type: hivex-wildfire-resource-management
-    metrics:
-    - type: cumulative_reward
-      value: 1093.1187683105468 +/- 578.7491242760859
-      name: Cumulative Reward
-      verified: true
-    - type: collective_performance
-      value: 71.27123718261718 +/- 32.09683856042925
-      name: Collective Performance
-      verified: true
-    - type: individual_performance
-      value: 35.614274978637695 +/- 15.634065158512929
-      name: Individual Performance
-      verified: true
-    - type: reward_for_moving_resources_to_neighbours
-      value: 914.6083679199219 +/- 397.64001336221355
-      name: Reward for Moving Resources to Neighbours
-      verified: true
-    - type: reward_for_moving_resources_to_self
-      value: 0.5484737113118172 +/- 0.339556676622338
-      name: Reward for Moving Resources to Self
-      verified: true
----
+---
+library_name: hivex
+original_train_name: WildfireResourceManagement_difficulty_4_task_2_run_id_0_train
+tags:
+- hivex
+- hivex-wildfire-resource-management
+- reinforcement-learning
+- multi-agent-reinforcement-learning
+model-index:
+- name: hivex-WRM-PPO-baseline-task-2-difficulty-4
+  results:
+  - task:
+      type: sub-task
+      name: distribute_all
+      task-id: 2
+      difficulty-id: 4
+    dataset:
+      name: hivex-wildfire-resource-management
+      type: hivex-wildfire-resource-management
+    metrics:
+    - type: cumulative_reward
+      value: 1093.1187683105468 +/- 578.7491242760859
+      name: Cumulative Reward
+      verified: true
+    - type: collective_performance
+      value: 71.27123718261718 +/- 32.09683856042925
+      name: Collective Performance
+      verified: true
+    - type: individual_performance
+      value: 35.614274978637695 +/- 15.634065158512929
+      name: Individual Performance
+      verified: true
+    - type: reward_for_moving_resources_to_neighbours
+      value: 914.6083679199219 +/- 397.64001336221355
+      name: Reward for Moving Resources to Neighbours
+      verified: true
+    - type: reward_for_moving_resources_to_self
+      value: 0.5484737113118172 +/- 0.339556676622338
+      name: Reward for Moving Resources to Self
+      verified: true
+---
+
+This model serves as the baseline for the **Wildfire Resource Management** environment, trained and tested on task <code>2</code> with difficulty <code>4</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
+
+Environment: **Wildfire Resource Management**<br>
+Task: <code>2</code><br>
+Difficulty: <code>4</code><br>
+Algorithm: <code>PPO</code><br>
+Episode Length: <code>500</code><br>
+Training <code>max_steps</code>: <code>450000</code><br>
+Testing <code>max_steps</code>: <code>45000</code><br><br>
+
+Train & Test [Scripts](https://github.com/hivex-research/hivex)<br>
+Download the [Environment](https://github.com/hivex-research/hivex-environments)