This model serves as the baseline for the Wildfire Resource Management environment, trained and tested on task 0 with difficulty 7 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Wildfire Resource Management
Task: 0
Difficulty: 7
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-reported115.5483470916748 +/- 33.54802987989145
- Collective Performance on hivex-wildfire-resource-managementself-reported44.748003768920896 +/- 10.01290846231668
- Individual Performance on hivex-wildfire-resource-managementself-reported24.67834577560425 +/- 6.925884463468533
- Reward for Moving Resources to Neighbours on hivex-wildfire-resource-managementself-reported64.52305927276612 +/- 22.579827069648683
- Reward for Moving Resources to Self on hivex-wildfire-resource-managementself-reported1.243993028998375 +/- 0.9987439451375053