This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 2 with difficulty 4 using the Proximal Policy Optimization (PPO) algorithm.

Environment: Aerial Wildfire Suppression
Task: 2
Difficulty: 4
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000

Train & Test Scripts
Download the Environment

Downloads last month: -; Downloads are not tracked for this model. How to track

Video Preview

Reinforcement Learning

Collection including hivex-research/hivex-AWS-PPO-baseline-task-2-difficulty-4

Aerial Wildfire Suppression

Collection

89 items • Updated 10 days ago

Evaluation results

Crash Count on hivex-aerial-wildfire-suppression
self-reported

0.2666666738688946 +/- 0.21220094741551065
Extinguishing Trees on hivex-aerial-wildfire-suppression
self-reported

15.033333298563957 +/- 25.090456231376915
Extinguishing Trees Reward on hivex-aerial-wildfire-suppression
self-reported

75.16666680574417 +/- 125.45228120233335
Fire Out on hivex-aerial-wildfire-suppression
self-reported

0.08333333507180214 +/- 0.19117978221378917
Fire too Close to City on hivex-aerial-wildfire-suppression
self-reported

0.65 +/- 0.4006573545930159
Preparing Trees on hivex-aerial-wildfire-suppression
self-reported

698.3916749000549 +/- 592.6497869663837
Preparing Trees Reward on hivex-aerial-wildfire-suppression
self-reported

3491.958309555054 +/- 2963.248872852455
Water Drop on hivex-aerial-wildfire-suppression
self-reported

37.541666984558105 +/- 19.128060369297387
Water Pickup on hivex-aerial-wildfire-suppression
self-reported

37.23333339691162 +/- 18.986482878845344
Cumulative Reward on hivex-aerial-wildfire-suppression
self-reported

3759.337190246582 +/- 2254.2074397931997

View on Papers With Code