---
library_name: hivex
original_train_name: AerialWildfireSuppression_difficulty_2_task_2_run_id_2_train
tags:
- hivex
- hivex-aerial-wildfire-suppression
- reinforcement-learning
- multi-agent-reinforcement-learning
model-index:
- name: hivex-AWS-PPO-baseline-task-2-difficulty-2
  results:
  - task:
      type: sub-task
      name: maximize_preparing_non_burning_trees
      task-id: 2
      difficulty-id: 2
    dataset:
      name: hivex-aerial-wildfire-suppression
      type: hivex-aerial-wildfire-suppression
    metrics:
    - type: crash_count
      value: 0.12222222536802292 +/- 0.16381577701779051
      name: Crash Count
      verified: true
    - type: extinguishing_trees
      value: 6.599999992549419 +/- 15.242522731448657
      name: Extinguishing Trees
      verified: true
    - type: extinguishing_trees_reward
      value: 32.9999993622303 +/- 76.21261195341214
      name: Extinguishing Trees Reward
      verified: true
    - type: fire_out
      value: 0.3138888914138079 +/- 0.4019425711973155
      name: Fire Out
      verified: true
    - type: fire_too_close_to_city
      value: 0.6666666671633721 +/- 0.44261318597616683
      name: Fire too Close to City
      verified: true
    - type: preparing_trees
      value: 747.7777755737304 +/- 635.3383235803965
      name: Preparing Trees
      verified: true
    - type: preparing_trees_reward
      value: 3738.888851928711 +/- 3176.691613050029
      name: Preparing Trees Reward
      verified: true
    - type: water_drop
      value: 23.388888955116272 +/- 12.81474416895113
      name: Water Drop
      verified: true
    - type: water_pickup
      value: 22.874999976158144 +/- 12.792184644801207
      name: Water Pickup
      verified: true
    - type: cumulative_reward
      value: 3947.1150146484374 +/- 2234.072313108481
      name: Cumulative Reward
      verified: true
---

This model serves as the baseline for the **Aerial Wildfire Suppression** environment, trained and tested on task <code>2</code> with difficulty <code>2</code> using the Proximal Policy Optimization (PPO) algorithm.<br><br>

Environment: **Aerial Wildfire Suppression**<br>
Task: <code>2</code><br>
Difficulty: <code>2</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)