This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 2 with difficulty 6 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 2
Difficulty: 6
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-reported0.11666667014360428 +/- 0.18809603682131015
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported26.57500003799796 +/- 36.448371998578736
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported132.87500058710575 +/- 182.24186375120422
- Fire Out on hivex-aerial-wildfire-suppressionself-reported0.3166666701436043 +/- 0.4114586821666224
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.95 +/- 0.15389675281277315
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported637.158332157135 +/- 502.3677062623285
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported3185.791680145264 +/- 2511.8385615224347
- Water Drop on hivex-aerial-wildfire-suppressionself-reported81.89166564941407 +/- 40.19878442392626
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported81.56666650772095 +/- 40.211261838762134
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported3751.6249725341795 +/- 3124.340359471712