This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 0 with difficulty 7 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 0
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-reported0.13333333730697633 +/- 0.1585755350905039
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported20.61666655242443 +/- 31.49538645519398
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported103.08333207368851 +/- 157.4769288508104
- Fire Out on hivex-aerial-wildfire-suppressionself-reported0.18333333730697632 +/- 0.31483775244365086
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.975 +/- 0.11180339887498947
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported652.3000063419342 +/- 754.7335526661299
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported652.3000063419342 +/- 754.7335526661299
- Water Drop on hivex-aerial-wildfire-suppressionself-reported56.241666316986084 +/- 36.06428926662349
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported55.76666698455811 +/- 35.96926061643514
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported728.9100012302399 +/- 710.9909405090588