This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 4 with difficulty 9 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 4
Difficulty: 9
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-reported0.996428570151329 +/- 0.015971919837000092
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported0.04055555630475283 +/- 0.1275818509161524
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported0.20277777537703515 +/- 0.6379092306314261
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.004545454680919647 +/- 0.020327891310361893
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported276.61525497436526 +/- 33.81716366148196
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported276.61525497436526 +/- 33.81716366148196
- Water Drop on hivex-aerial-wildfire-suppressionself-reported2.0456768214702605 +/- 0.4084652912050666
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported2.0456768214702605 +/- 0.4084652912050666
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported177.27129974365235 +/- 36.12212164713132