This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 3 with difficulty 9 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 3
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-reported0.0833333358168602 +/- 0.12681432215480823
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported40.43333244919777 +/- 89.55848904778
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported202.1666701555252 +/- 447.79246693057974
- Fire Out on hivex-aerial-wildfire-suppressionself-reported0.31666667088866235 +/- 0.38578544750821686
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.975 +/- 0.11180339887498947
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported889.5999923229217 +/- 798.283831409951
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported889.5999923229217 +/- 798.283831409951
- Water Drop on hivex-aerial-wildfire-suppressionself-reported46.18333358764649 +/- 23.596319104972988
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported45.63333377838135 +/- 23.684241605268586
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported1184.7800241470336 +/- 941.7770730791063