This model serves as the baseline for the Wildfire Resource Management environment, trained and tested on task 1 with difficulty 4 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Wildfire Resource Management
Task: 1
Difficulty: 4
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-reported417.6073974609375 +/- 190.19011561647912
- Collective Performance on hivex-wildfire-resource-managementself-reported72.88476066589355 +/- 36.648931872523086
- Individual Performance on hivex-wildfire-resource-managementself-reported37.18313026428223 +/- 17.18048840702159
- Reward for Moving Resources to Neighbours on hivex-wildfire-resource-managementself-reported1.0694182068109512 +/- 0.452972812288188
- Reward for Moving Resources to Self on hivex-wildfire-resource-managementself-reported324.34189453125 +/- 153.73020446695705