This model serves as the baseline for the Wildfire Resource Management environment, trained and tested on task 2 with difficulty 2 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Wildfire Resource Management
Task: 2
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-reported719.8077911376953 +/- 176.60168760638808
- Collective Performance on hivex-wildfire-resource-managementself-reported49.83914451599121 +/- 17.927922628117184
- Individual Performance on hivex-wildfire-resource-managementself-reported26.82857608795166 +/- 10.644374836699683
- Reward for Moving Resources to Neighbours on hivex-wildfire-resource-managementself-reported670.3809020996093 +/- 354.66801295508003
- Reward for Moving Resources to Self on hivex-wildfire-resource-managementself-reported0.3922588244080544 +/- 0.20202251712801628