This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 4 with difficulty 1 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 4
Difficulty: 1
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-reported0.6166666761040688 +/- 0.22360679529482064
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported0.4333333492279053 +/- 1.9379256515825043
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported2.166666603088379 +/- 9.689627618168343
- Fire Out on hivex-aerial-wildfire-suppressionself-reported0.05833333507180214 +/- 0.11180340220699042
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.425 +/- 0.37257991018529735
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported210.27499961853027 +/- 101.36103492999625
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported210.27499961853027 +/- 101.36103492999625
- Water Drop on hivex-aerial-wildfire-suppressionself-reported3.3749999940395354 +/- 2.19507356485688
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported3.2916666686534883 +/- 2.260695820449611
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported-69.60107120275498 +/- 211.17136032627994