This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 6 with difficulty 2 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 6
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-reported0.029796552332118153 +/- 0.013558095195825941
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported0.3805455264635384 +/- 0.49240092917648515
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported1.9027276199311018 +/- 2.462004661948154
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported182.82622451782225 +/- 11.38041138346274
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported182.82622451782225 +/- 11.38041138346274
- Water Drop on hivex-aerial-wildfire-suppressionself-reported0.9693701088428497 +/- 0.015894927913693367
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported181.8419204711914 +/- 12.238550390744056