This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 0 with difficulty 2 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 0
Difficulty: 2
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-reported0.17500000447034836 +/- 0.20572934505430354
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported11.175000129640102 +/- 18.059880604876085
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported55.874999076128006 +/- 90.29940061063385
- Fire Out on hivex-aerial-wildfire-suppressionself-reported0.28333333805203437 +/- 0.34666329618689634
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.825 +/- 0.3354101966249685
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported663.6749959468841 +/- 454.0686107184048
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported663.6749959468841 +/- 454.0686107184048
- Water Drop on hivex-aerial-wildfire-suppressionself-reported34.224999928474425 +/- 17.930769804240374
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported33.84999995231628 +/- 17.957706990252632
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported749.1333358764648 +/- 395.7873496420998