Update README.md

README.md

@@ -1,33 +1,46 @@
----
-library_name: hivex
-original_train_name: WindFarmControl_pattern_8_task_1_run_id_2_train
-tags:
-- hivex
-- hivex-wind-farm-control
-- reinforcement-learning
-- multi-agent-reinforcement-learning
-model-index:
-- name: hivex-WFC-PPO-baseline-task-1-pattern-8
-  results:
-  - task:
-      type: sub-task
-      name: avoid_damage
-      task-id: 1
-      pattern-id: 8
-    dataset:
-      name: hivex-wind-farm-control
-      type: hivex-wind-farm-control
-    metrics:
-    - type: cumulative_reward
-      value: 4809.995881347656 +/- 59.342603372525524
-      name: Cumulative Reward
-      verified: true
-    - type: avoid_damage_reward
-      value: 4810.060444335937 +/- 62.5605922005838
-      name: Avoid Damage Reward
-      verified: true
-    - type: individual_performance
-      value: 0.0 +/- 0.0
-      name: Individual Performance
-      verified: true
----
+---
+library_name: hivex
+original_train_name: WindFarmControl_pattern_8_task_1_run_id_2_train
+tags:
+- hivex
+- hivex-wind-farm-control
+- reinforcement-learning
+- multi-agent-reinforcement-learning
+model-index:
+- name: hivex-WFC-PPO-baseline-task-1-pattern-8
+  results:
+  - task:
+      type: sub-task
+      name: avoid_damage
+      task-id: 1
+      pattern-id: 8
+    dataset:
+      name: hivex-wind-farm-control
+      type: hivex-wind-farm-control
+    metrics:
+    - type: cumulative_reward
+      value: 4809.995881347656 +/- 59.342603372525524
+      name: Cumulative Reward
+      verified: true
+    - type: avoid_damage_reward
+      value: 4810.060444335937 +/- 62.5605922005838
+      name: Avoid Damage Reward
+      verified: true
+    - type: individual_performance
+      value: 0.0 +/- 0.0
+      name: Individual Performance
+      verified: true
+---
+
+This model serves as the baseline for the **Wind Farm Control** environment, trained and tested on task <code>1</code> with pattern <code>8</code> using the Proximal Policy Optimization (PPO) algorithm.<br>
+<br>
+Environment: **Wind Farm Control**<br>
+Task: <code>1</code><br>
+Pattern: <code>8</code><br>
+Algorithm: <code>PPO</code><br>
+Episode Length: <code>5000</code><br>
+Training <code>max_steps</code>: <code>8000000</code><br>
+Testing <code>max_steps</code>: <code>8000000</code><br>
+<br>
+Train & Test [Scripts](https://github.com/hivex-research/hivex)<br>
+Download the [Environment](https://github.com/hivex-research/hivex-environments)