This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 4 with difficulty 3 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 4
Difficulty: 3
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-reported0.995833334326744 +/- 0.01863389536983029
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported0.2034926237538457 +/- 0.4116170031592015
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported1.0174630872905255 +/- 2.0580849483100514
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.026969697698950766 +/- 0.04238606278064562
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported222.16366958618164 +/- 30.50323526327436
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported222.16366958618164 +/- 30.50323526327436
- Water Drop on hivex-aerial-wildfire-suppressionself-reported1.5261266589164735 +/- 0.27324174769670806
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported1.5261266589164735 +/- 0.27324174769670806
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported112.0983154296875 +/- 26.748844898286993