This model serves as the baseline for the Wildfire Resource Management environment, trained and tested on task 0 with difficulty 8 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Wildfire Resource Management
Task: 0
Difficulty: 8
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-reported150.93561477661132 +/- 76.23284307650627
- Collective Performance on hivex-wildfire-resource-managementself-reported61.58133754730225 +/- 33.127614095127164
- Individual Performance on hivex-wildfire-resource-managementself-reported32.567462825775145 +/- 17.909844518650875
- Reward for Moving Resources to Neighbours on hivex-wildfire-resource-managementself-reported81.31805839538575 +/- 40.93007534940363
- Reward for Moving Resources to Self on hivex-wildfire-resource-managementself-reported0.5046550706028938 +/- 0.5512559684915638