This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 2 with difficulty 7 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 2
Difficulty: 7
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-reported0.41666667610406877 +/- 0.29369595331135534
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported26.98611140549183 +/- 45.067904043919626
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported134.9305568575859 +/- 225.33952073669184
- Fire Out on hivex-aerial-wildfire-suppressionself-reported0.09166666939854622 +/- 0.1375963286810061
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.9833333343267441 +/- 0.07453559480732508
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported915.0361038208008 +/- 630.722632747104
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported4575.180584716797 +/- 3153.613200762862
- Water Drop on hivex-aerial-wildfire-suppressionself-reported63.81111078262329 +/- 27.460713193319517
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported63.5777774810791 +/- 27.43349377033259
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported4956.189190673828 +/- 2576.604065716017