This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 4 with difficulty 5 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 4
Difficulty: 5
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-reported0.9886904746294022 +/- 0.02771131517144696
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported0.08853785246610642 +/- 0.18335850809661372
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported0.4426892638206482 +/- 0.9167925407962902
- Fire Out on hivex-aerial-wildfire-suppressionself-reported0.00773809552192688 +/- 0.02389552224594306
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.008712121471762656 +/- 0.026843490782201274
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported273.38488922119143 +/- 40.98115816740078
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported273.38488922119143 +/- 40.98115816740078
- Water Drop on hivex-aerial-wildfire-suppressionself-reported1.757782220840454 +/- 0.286049469501929
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported1.7500441253185273 +/- 0.2868768059725031
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported172.30555000305176 +/- 38.100567507916715