This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 6 with difficulty 9 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 6
Difficulty: 9
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000
Train & Test Scripts
Download the Environment
Evaluation results
- Crash Count on hivex-aerial-wildfire-suppressionself-reported0.01373663340928033 +/- 0.006368126725441811
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported0.20510363813955337 +/- 0.13931107935070292
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported1.0255182035267354 +/- 0.6965553894409803
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported282.37622985839846 +/- 6.297463507454497
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported282.37622985839846 +/- 6.297463507454497
- Water Drop on hivex-aerial-wildfire-suppressionself-reported0.9859137117862702 +/- 0.006026457217121745
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported0.0010042423149570824 +/- 0.0014968736951810181
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported282.1384475708008 +/- 6.797800299539885