This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 2 with difficulty 3 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 2
Difficulty: 3
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 +/- 0.1378617027533506
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported18.683333218097687 +/- 27.558120115325824
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported93.41666712760926 +/- 137.79060314424476
- Fire Out on hivex-aerial-wildfire-suppressionself-reported0.35833333656191824 +/- 0.36784102365159543
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.975 +/- 0.11180339887498947
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported556.9166661500931 +/- 491.4252421024537
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported2784.5833506584167 +/- 2457.1262108957085
- Water Drop on hivex-aerial-wildfire-suppressionself-reported39.591666674613954 +/- 20.687346400193867
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported39.18333334922791 +/- 20.631967029054877
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported2911.9833114624025 +/- 2372.473518108635