|
--- |
|
library_name: hivex |
|
original_train_name: WindFarmControl_pattern_6_task_1_run_id_1_train |
|
tags: |
|
- hivex |
|
- hivex-wind-farm-control |
|
- reinforcement-learning |
|
- multi-agent-reinforcement-learning |
|
model-index: |
|
- name: hivex-WFC-PPO-baseline-task-1-pattern-6 |
|
results: |
|
- task: |
|
type: sub-task |
|
name: avoid_damage |
|
task-id: 1 |
|
pattern-id: 6 |
|
dataset: |
|
name: hivex-wind-farm-control |
|
type: hivex-wind-farm-control |
|
metrics: |
|
- type: cumulative_reward |
|
value: 4821.655510253906 +/- 37.888594391723174 |
|
name: Cumulative Reward |
|
verified: true |
|
- type: avoid_damage_reward |
|
value: 4821.617194824219 +/- 38.82408699722769 |
|
name: Avoid Damage Reward |
|
verified: true |
|
- type: individual_performance |
|
value: 0.0 +/- 0.0 |
|
name: Individual Performance |
|
verified: true |
|
--- |
|
|
|
This model serves as the baseline for the **Wind Farm Control** environment, trained and tested on task <code>1</code> with pattern <code>6</code> using the Proximal Policy Optimization (PPO) algorithm.<br> |
|
<br> |
|
Environment: **Wind Farm Control**<br> |
|
Task: <code>1</code><br> |
|
Pattern: <code>6</code><br> |
|
Algorithm: <code>PPO</code><br> |
|
Episode Length: <code>5000</code><br> |
|
Training <code>max_steps</code>: <code>8000000</code><br> |
|
Testing <code>max_steps</code>: <code>8000000</code><br> |
|
<br> |
|
Train & Test [Scripts](https://github.com/hivex-research/hivex)<br> |
|
Download the [Environment](https://github.com/hivex-research/hivex-environments) |
