Edit model card

This model serves as the baseline for the Aerial Wildfire Suppression environment, trained and tested on task 0 with difficulty 10 using the Proximal Policy Optimization (PPO) algorithm.

Environment: Aerial Wildfire Suppression
Task: 0
Difficulty: 10
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

Evaluation results

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

0.3416666768491268 +/- 0.20572934629325312
Extinguishing Trees on hivex-aerial-wildfire-suppression
self-reported

22.541666667163373 +/- 44.01873186547685
Extinguishing Trees Reward on hivex-aerial-wildfire-suppression
self-reported

112.70833333134651 +/- 220.0936595589533
Fire Out on hivex-aerial-wildfire-suppression
self-reported

0.07500000223517418 +/- 0.1750104476777611
Fire too Close to City on hivex-aerial-wildfire-suppression
self-reported

0.875 +/- 0.31933318682925255
Preparing Trees on hivex-aerial-wildfire-suppression
self-reported

674.8416697263717 +/- 544.8041855624299
Preparing Trees Reward on hivex-aerial-wildfire-suppression
self-reported

674.8416697263717 +/- 544.8041855624299
Water Drop on hivex-aerial-wildfire-suppression
self-reported

49.54999938011169 +/- 18.605090713043403
Water Pickup on hivex-aerial-wildfire-suppression
self-reported

49.26666617393494 +/- 18.509156507840594
Cumulative Reward on hivex-aerial-wildfire-suppression
self-reported

880.1708267211914 +/- 503.11196457140045

View on Papers With Code