This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 0 with difficulty 9 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 0
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-reported0.24166667386889457 +/- 0.1750104476777611
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported17.141666746139528 +/- 39.513165920891936
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported85.70833311080932 +/- 197.56582920337453
- Fire Out on hivex-aerial-wildfire-suppressionself-reported0.12500000223517418 +/- 0.24106852927463382
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.9 +/- 0.2615741818902984
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported721.7666670084 +/- 737.4681856167363
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported721.7666670084 +/- 737.4681856167363
- Water Drop on hivex-aerial-wildfire-suppressionself-reported66.28333377838135 +/- 30.644495531353783
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported65.93333344459533 +/- 30.521844562150648
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported996.1558359742164 +/- 875.8416918638716