Update README.md

README.md

@@ -1,41 +1,54 @@
----
-library_name: hivex
-original_train_name: WildfireResourceManagement_difficulty_1_task_1_run_id_0_train
-tags:
-- hivex
-- hivex-wildfire-resource-management
-- reinforcement-learning
-- multi-agent-reinforcement-learning
-model-index:
-- name: hivex-WRM-PPO-baseline-task-1-difficulty-1
-  results:
-  - task:
-      type: sub-task
-      name: keep_all
-      task-id: 1
-      difficulty-id: 1
-    dataset:
-      name: hivex-wildfire-resource-management
-      type: hivex-wildfire-resource-management
-    metrics:
-    - type: cumulative_reward
-      value: 195.4663185119629 +/- 77.65158484674649
-      name: Cumulative Reward
-      verified: true
-    - type: collective_performance
-      value: 34.28780403137207 +/- 10.980421619205345
-      name: Collective Performance
-      verified: true
-    - type: individual_performance
-      value: 16.798346424102782 +/- 5.2696319909880085
-      name: Individual Performance
-      verified: true
-    - type: reward_for_moving_resources_to_neighbours
-      value: 1.2929230749607086 +/- 0.5330753884066604
-      name: Reward for Moving Resources to Neighbours
-      verified: true
-    - type: reward_for_moving_resources_to_self
-      value: 143.07430686950684 +/- 44.849034918704156
-      name: Reward for Moving Resources to Self
-      verified: true
----
+---
+library_name: hivex
+original_train_name: WildfireResourceManagement_difficulty_1_task_1_run_id_0_train
+tags:
+- hivex
+- hivex-wildfire-resource-management
+- reinforcement-learning
+- multi-agent-reinforcement-learning
+model-index:
+- name: hivex-WRM-PPO-baseline-task-1-difficulty-1
+  results:
+  - task:
+      type: sub-task
+      name: keep_all
+      task-id: 1
+      difficulty-id: 1
+    dataset:
+      name: hivex-wildfire-resource-management
+      type: hivex-wildfire-resource-management
+    metrics:
+    - type: cumulative_reward
+      value: 195.4663185119629 +/- 77.65158484674649
+      name: Cumulative Reward
+      verified: true
+    - type: collective_performance
+      value: 34.28780403137207 +/- 10.980421619205345
+      name: Collective Performance
+      verified: true
+    - type: individual_performance
+      value: 16.798346424102782 +/- 5.2696319909880085
+      name: Individual Performance
+      verified: true
+    - type: reward_for_moving_resources_to_neighbours
+      value: 1.2929230749607086 +/- 0.5330753884066604
+      name: Reward for Moving Resources to Neighbours
+      verified: true
+    - type: reward_for_moving_resources_to_self
+      value: 143.07430686950684 +/- 44.849034918704156
+      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>1</code> with difficulty <code>1</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>
+
+Environment: **Wildfire Resource Management**<br>
+Task: <code>1</code><br>
+Difficulty: <code>1</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)