This model serves as the baseline for the Wildfire Resource Management environment, trained and tested on task 0 with difficulty 6 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Wildfire Resource Management
Task: 0
Difficulty: 6
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-reported107.97416267395019 +/- 48.20278489614717
- Collective Performance on hivex-wildfire-resource-managementself-reported46.81386375427246 +/- 21.01886010155952
- Individual Performance on hivex-wildfire-resource-managementself-reported23.57359619140625 +/- 10.460954413923357
- Reward for Moving Resources to Neighbours on hivex-wildfire-resource-managementself-reported57.37900886535645 +/- 29.412938343401375
- Reward for Moving Resources to Self on hivex-wildfire-resource-managementself-reported0.5378097414970398 +/- 0.316862991497751