This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 1 with difficulty 2 using the Proximal Policy Optimization (PPO) algorithm.

Environment: Aerial Wildfire Suppression
Task: 1
Difficulty: 2
Algorithm: PPO
Episode Length: 3000
Training max_steps: 1800000
Testing max_steps: 180000

Train & Test Scripts
Download the Environment

Downloads last month: -; Downloads are not tracked for this model. How to track

Video Preview

Reinforcement Learning

Collection including hivex-research/hivex-AWS-PPO-baseline-task-1-difficulty-2

Aerial Wildfire Suppression

Collection

90 items • Updated Mar 20

Evaluation results

Crash Count on hivex-aerial-wildfire-suppression
self-reported

0.5083333425223827 +/- 0.2699330882907145
Extinguishing Trees on hivex-aerial-wildfire-suppression
self-reported

4.355555608123541 +/- 6.907337205240576
Extinguishing Trees Reward on hivex-aerial-wildfire-suppression
self-reported

217.77777848243713 +/- 345.36685865656506
Fire Out on hivex-aerial-wildfire-suppression
self-reported

0.03333333432674408 +/- 0.08719139656193886
Fire too Close to City on hivex-aerial-wildfire-suppression
self-reported

0.5000000014901161 +/- 0.38616422218364055
Preparing Trees on hivex-aerial-wildfire-suppression
self-reported

390.2111080169678 +/- 226.11041224327414
Preparing Trees Reward on hivex-aerial-wildfire-suppression
self-reported

390.2111080169678 +/- 226.11041224327414
Water Drop on hivex-aerial-wildfire-suppression
self-reported

6.283333307504654 +/- 3.095559538761643
Water Pickup on hivex-aerial-wildfire-suppression
self-reported

5.966666650772095 +/- 3.12197354808832
Cumulative Reward on hivex-aerial-wildfire-suppression
self-reported

546.4062370300293 +/- 319.2706067457673

View on Papers With Code