This model serves as the baseline for the Wildfire Resource Management environment, trained and tested on task 0 with difficulty 1 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Wildfire Resource Management
Task: 0
Difficulty: 1
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-reported93.91741180419922 +/- 37.05853273475244
- Collective Performance on hivex-wildfire-resource-managementself-reported34.50206546783447 +/- 11.805853483736035
- Individual Performance on hivex-wildfire-resource-managementself-reported18.018507194519042 +/- 6.813722115047946
- Reward for Moving Resources to Neighbours on hivex-wildfire-resource-managementself-reported49.37095775604248 +/- 24.763152240827306
- Reward for Moving Resources to Self on hivex-wildfire-resource-managementself-reported0.2246590718626976 +/- 0.10528075262454495