This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 0 with difficulty 1 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 0
Difficulty: 1
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-reported0.4638888962566853 +/- 0.22022125290367361
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported4.927777701616288 +/- 10.908043339081729
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported24.638889169692995 +/- 54.54021798933507
- Fire Out on hivex-aerial-wildfire-suppressionself-reported0.16944444850087165 +/- 0.26087460404732826
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.4000000014901161 +/- 0.4060939306276508
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported466.66389350891114 +/- 226.10086599763596
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported466.66389350891114 +/- 226.10086599763596
- Water Drop on hivex-aerial-wildfire-suppressionself-reported6.894444406032562 +/- 3.5710508499944695
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported6.702777767181397 +/- 3.5387613166964393
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported419.7281740188599 +/- 230.5992870123718