This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 1 with difficulty 5 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 1
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-reported0.15833333656191825 +/- 0.19098850564751765
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported20.000000047683717 +/- 35.87091048765571
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported999.9999992370606 +/- 1793.545528264617
- Fire Out on hivex-aerial-wildfire-suppressionself-reported0.10000000298023223 +/- 0.244231706300354
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.925 +/- 0.24468024246479642
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported439.2000018119812 +/- 486.4487458526075
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported439.2000018119812 +/- 486.4487458526075
- Water Drop on hivex-aerial-wildfire-suppressionself-reported35.9416666328907 +/- 21.80430457793747
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported35.77500002980232 +/- 21.714001930720748
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported1192.8983428001404 +/- 1401.6480393641084