This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 2 with difficulty 9 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 2
Difficulty: 9
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-reported0.09166666939854622 +/- 0.18317377972526547
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported8.949999886751176 +/- 12.562137901097202
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported44.75000040531158 +/- 62.81068995864626
- Fire Out on hivex-aerial-wildfire-suppressionself-reported0.3500000022351742 +/- 0.4114586818171751
- Fire too Close to City on hivex-aerial-wildfire-suppressionself-reported0.975 +/- 0.11180339887498947
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported652.12500230968 +/- 512.4888000138135
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported3260.6250272393227 +/- 2562.444032266141
- Water Drop on hivex-aerial-wildfire-suppressionself-reported65.37499959468842 +/- 34.89231000298373
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported64.99166650772095 +/- 34.92349427276053
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported3682.374974441528 +/- 2239.4285326262125