This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 6 with difficulty 4 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 6
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-reported0.019636338157579303 +/- 0.006296536151540525
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported0.20098300511017442 +/- 0.20730763026051913
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported1.0049150258302688 +/- 1.0365381477211943
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported257.4399574279785 +/- 10.902792920729194
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported257.4399574279785 +/- 10.902792920729194
- Water Drop on hivex-aerial-wildfire-suppressionself-reported0.9798782348632813 +/- 0.007123928367457922
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported0.000187265919521451 +/- 0.0008374786518379387
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported256.58973693847656 +/- 11.54790983559329