This model serves as the baseline for the Wildfire Resource Management environment, trained and tested on task 0 with difficulty 2 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Wildfire Resource Management
Task: 0
Difficulty: 2
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-reported115.81460418701172 +/- 26.078782597878128
- Collective Performance on hivex-wildfire-resource-managementself-reported51.81407127380371 +/- 18.776135090696116
- Individual Performance on hivex-wildfire-resource-managementself-reported27.154735565185547 +/- 10.446210720821945
- Reward for Moving Resources to Neighbours on hivex-wildfire-resource-managementself-reported60.09906158447266 +/- 33.42797696299573
- Reward for Moving Resources to Self on hivex-wildfire-resource-managementself-reported2.2813201546669006 +/- 1.1529928776928962