---
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_9_task_6_run_id_2_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-6-difficulty-9
  results:
  - task:
      type: sub-task
      name: drop_water
      task-id: 6
      difficulty-id: 9
    dataset:
      name: hivex-aerial-wildfire-suppression
      type: hivex-aerial-wildfire-suppression
    metrics:
    - type: crash_count
      value: 0.01373663340928033 +/- 0.006368126725441811
      name: Crash Count
      verified: true
    - type: extinguishing_trees
      value: 0.20510363813955337 +/- 0.13931107935070292
      name: Extinguishing Trees
      verified: true
    - type: extinguishing_trees_reward
      value: 1.0255182035267354 +/- 0.6965553894409803
      name: Extinguishing Trees Reward
      verified: true
    - type: preparing_trees
      value: 282.37622985839846 +/- 6.297463507454497
      name: Preparing Trees
      verified: true
    - type: preparing_trees_reward
      value: 282.37622985839846 +/- 6.297463507454497
      name: Preparing Trees Reward
      verified: true
    - type: water_drop
      value: 0.9859137117862702 +/- 0.006026457217121745
      name: Water Drop
      verified: true
    - type: water_pickup
      value: 0.0010042423149570824 +/- 0.0014968736951810181
      name: Water Pickup
      verified: true
    - type: cumulative_reward
      value: 282.1384475708008 +/- 6.797800299539885
      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>9</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>

Environment: **Aerial Wildfire Suppression**<br>
Task: <code>6</code><br>
Difficulty: <code>9</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)