This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 3 with difficulty 4 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 3
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-reported0.12500000223517418 +/- 0.17832062789523476
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported12.74999994635582 +/- 16.512222842027622
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported63.74999964237213 +/- 82.56111388966389
- Fire Out on hivex-aerial-wildfire-suppressionself-reported0.2833333358168602 +/- 0.3711055092960568
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.875 +/- 0.2221308291596596
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported754.1750064849854 +/- 639.6152297445449
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported754.1750064849854 +/- 639.6152297445449
- Water Drop on hivex-aerial-wildfire-suppressionself-reported27.541666519641876 +/- 14.354622400373676
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported27.24166692495346 +/- 14.290989756251832
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported763.3192396879197 +/- 649.6844365742547