This model serves as the baseline for the Wildfire Resource Management environment, trained and tested on task 2 with difficulty 9 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Wildfire Resource Management
Task: 2
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-reported706.2242218017578 +/- 366.5585998786708
- Collective Performance on hivex-wildfire-resource-managementself-reported44.51871128082276 +/- 17.473789150365352
- Individual Performance on hivex-wildfire-resource-managementself-reported23.007067108154295 +/- 9.167235768307094
- Reward for Moving Resources to Neighbours on hivex-wildfire-resource-managementself-reported610.6411285400391 +/- 372.33275333579104
- Reward for Moving Resources to Self on hivex-wildfire-resource-managementself-reported0.18396489545702935 +/- 0.1088332788046387