This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 6 with difficulty 1 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 6
Difficulty: 1
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-reported0.040009206905961034 +/- 0.018735561549171307
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported0.4969854736700654 +/- 0.6300676451261423
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported2.484927378222346 +/- 3.150338277465211
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported143.18572998046875 +/- 12.10208288767324
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported143.18572998046875 +/- 12.10208288767324
- Water Drop on hivex-aerial-wildfire-suppressionself-reported0.9589269667863846 +/- 0.018643650861373894
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported141.81843147277831 +/- 13.9801382441756