This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 2 with difficulty 5 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 2
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-reported0.25000000521540644 +/- 0.26765169236445613
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported26.541666515916585 +/- 71.99835260789617
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported132.70833393633364 +/- 359.9917639236706
- Fire Out on hivex-aerial-wildfire-suppressionself-reported0.1916666693985462 +/- 0.3301381975702533
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.975 +/- 0.11180339887498947
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported884.999996471405 +/- 751.8528699660257
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported4425.0000263214115 +/- 3759.264413506219
- Water Drop on hivex-aerial-wildfire-suppressionself-reported53.89166679382324 +/- 27.40039192850323
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported53.56666660308838 +/- 27.298244112627053
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported5174.121683979034 +/- 4124.406680944283