This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 4 with difficulty 2 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 4
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-reported0.9954545468091964 +/- 0.020327884646360022
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported0.28887686133384705 +/- 0.6787165224682201
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported1.4443842768669128 +/- 3.393582550370347
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.023333333805203436 +/- 0.052815469164145035
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported173.5697063446045 +/- 22.599638913107242
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported173.5697063446045 +/- 22.599638913107242
- Water Drop on hivex-aerial-wildfire-suppressionself-reported1.2260812371969223 +/- 0.2007275933789739
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported1.2260812371969223 +/- 0.2007275933789739
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported65.80658979415894 +/- 25.50451599293347