This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 3 with difficulty 2 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 3
Difficulty: 2
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-reported0.06666666865348816 +/- 0.13679711768822556
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported1.45 +/- 3.3495657386738666
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported7.249999952316284 +/- 16.74782867264003
- Fire Out on hivex-aerial-wildfire-suppressionself-reported0.3527777805924416 +/- 0.4007283026646903
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.716666667163372 +/- 0.4192028074228474
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported255.98055567741395 +/- 148.28355870416527
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported255.98055567741395 +/- 148.28355870416527
- Water Drop on hivex-aerial-wildfire-suppressionself-reported19.411111223697663 +/- 13.424328820382387
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported19.355555641651154 +/- 13.43296587945375
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported259.08557624816893 +/- 165.96403709055332