This model serves as the baseline for the Wildfire Resource Management environment, trained and tested on task 1 with difficulty 1 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Wildfire Resource Management
Task: 1
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-reported195.4663185119629 +/- 77.65158484674649
- Collective Performance on hivex-wildfire-resource-managementself-reported34.28780403137207 +/- 10.980421619205345
- Individual Performance on hivex-wildfire-resource-managementself-reported16.798346424102782 +/- 5.2696319909880085
- Reward for Moving Resources to Neighbours on hivex-wildfire-resource-managementself-reported1.2929230749607086 +/- 0.5330753884066604
- Reward for Moving Resources to Self on hivex-wildfire-resource-managementself-reported143.07430686950684 +/- 44.849034918704156