This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 6 with difficulty 5 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 6
Difficulty: 5
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-reported0.022751575300935654 +/- 0.009602885208751202
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported0.2077373639680445 +/- 0.1507774190085061
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported1.0386868014931678 +/- 0.753887068245034
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported275.6179458618164 +/- 12.486733727275665
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported275.6179458618164 +/- 12.486733727275665
- Water Drop on hivex-aerial-wildfire-suppressionself-reported0.9767484277486801 +/- 0.00989079886411895
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported0.0005922459880821407 +/- 0.0015700193469281448
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported274.48731155395507 +/- 13.254462171454286