This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 6 with difficulty 7 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Aerial Wildfire Suppression
Task: 6
Difficulty: 7
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-reported0.015272001700941474 +/- 0.008560343748877621
- Extinguishing Trees on hivex-aerial-wildfire-suppressionself-reported0.16764693087898194 +/- 0.19795760638271612
- Extinguishing Trees Reward on hivex-aerial-wildfire-suppressionself-reported0.8382346628699452 +/- 0.9897880220029962
- Preparing Trees on hivex-aerial-wildfire-suppressionself-reported295.1830795288086 +/- 11.336644749563497
- Preparing Trees Reward on hivex-aerial-wildfire-suppressionself-reported295.1830795288086 +/- 11.336644749563497
- Water Drop on hivex-aerial-wildfire-suppressionself-reported0.9843656837940216 +/- 0.008887930230304724
- Water Pickup on hivex-aerial-wildfire-suppressionself-reported0.0007015933631919324 +/- 0.001493842309054032
- Cumulative Reward on hivex-aerial-wildfire-suppressionself-reported294.59887542724607 +/- 11.330578758684899