This model serves as the baseline for the Wildfire Resource Management environment, trained and tested on task 2 with difficulty 1 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Wildfire Resource Management
Task: 2
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-reported621.6318466186524 +/- 263.80346369019475
- Collective Performance on hivex-wildfire-resource-managementself-reported34.165497875213624 +/- 11.603925138407758
- Individual Performance on hivex-wildfire-resource-managementself-reported18.202730894088745 +/- 6.918594494920972
- Reward for Moving Resources to Neighbours on hivex-wildfire-resource-managementself-reported513.3224952697753 +/- 252.25941103189368
- Reward for Moving Resources to Self on hivex-wildfire-resource-managementself-reported0.18221199735999108 +/- 0.07358971280652664