This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 1 with difficulty 4 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 1
Difficulty: 4
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-reported0.00833333358168602 +/- 0.03726780073566347
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported15.225000095367431 +/- 25.73818226110129
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported761.2499908447265 +/- 1286.9091013360119
- Fire Out on hivex-aerial-wildfire-suppressionself-reported0.36666666716337204 +/- 0.4244018838665434
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.925 +/- 0.24468024246479642
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported651.3250035211444 +/- 627.0399351081593
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported651.3250035211444 +/- 627.0399351081593
- Water Drop on hivex-aerial-wildfire-suppressionself-reported46.266666889190674 +/- 26.519958404149136
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported45.76666655540466 +/- 26.436529035148055
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported1711.8633205413819 +/- 2423.7230528427467