This model serves as the baseline for the Wind Farm Control environment, trained and tested on task 1 with pattern 4 using the Proximal Policy Optimization (PPO) algorithm.
Environment: Wind Farm Control
Task: 1
Pattern: 4
Algorithm: PPO
Episode Length: 5000
Training max_steps: 8000000
Testing max_steps: 8000000
Train & Test Scripts
Download the Environment
Evaluation results
- Cumulative Reward on hivex-wind-farm-controlself-reported4816.654519042969 +/- 48.309486675816395
- Avoid Damage Reward on hivex-wind-farm-controlself-reported4816.70017578125 +/- 50.83180378290865
- Individual Performance on hivex-wind-farm-controlself-reported0.0 +/- 0.0