This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 6 with difficulty 10 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 6
Difficulty: 10
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-reported0.01919534709304571 +/- 0.004891916336268155
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported0.14774187933653593 +/- 0.21025496427030596
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported0.7387093845754862 +/- 1.0512748048411527
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported275.08778228759763 +/- 6.872679334348032
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported275.08778228759763 +/- 6.872679334348032
- Water Drop on hivex-aerial-wildfire-suppressionself-reported0.9804799735546113 +/- 0.0052643568095604555
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported0.0006513423752039671 +/- 0.0012320225884513893
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported273.9627319335938 +/- 7.442108906238094