This model serves as the baseline for the Wildfire Resource Management environment, trained and tested on task 0 with difficulty 9 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Wildfire Resource Management
Task: 0
Difficulty: 9
Algorithm: PPO
Episode Length: 500
Training max_steps: 450000
Testing max_steps: 45000
Train & Test Scripts
Download the Environment
Evaluation results
- Cumulative Reward on hivex-wildfire-resource-managementself-reported108.30524711608886 +/- 44.26496456209219
- Collective Performance on hivex-wildfire-resource-managementself-reported48.16655330657959 +/- 18.658942149744412
- Individual Performance on hivex-wildfire-resource-managementself-reported23.520054149627686 +/- 8.724727286979716
- Reward for Moving Resources to Neighbours on hivex-wildfire-resource-managementself-reported50.061480331420896 +/- 27.6190461058019
- Reward for Moving Resources to Self on hivex-wildfire-resource-managementself-reported3.3466444194316862 +/- 1.8331136243834456