This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 6 with difficulty 3 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 6
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-reported0.01590130275581032 +/- 0.009051027459662414
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported0.2118260153569281 +/- 0.3283880873127659
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported1.0591301042586565 +/- 1.641940515491148
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported234.83799896240234 +/- 10.68919451687246
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported234.83799896240234 +/- 10.68919451687246
- Water Drop on hivex-aerial-wildfire-suppressionself-reported0.9835368990898132 +/- 0.009798197368354513
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported0.000875470065511763 +/- 0.001850762177686202
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported234.31187438964844 +/- 9.555234680707661