REINFORCE Agent
This model was trained using the REINFORCE algorithm on the CartPole-v1 environment.
Environment
- CartPole-v1
Evaluation
| Metric | Value |
|---|---|
| Mean Reward | 500.0 |
| Standard Deviation | 0.0 |
| Certification Score | 500.0 |
Files
model.pt– Trained REINFORCE policyhyperparameters.json– Training hyperparametersresults.json– Evaluation resultsreplay.mp4– Gameplay replay
Evaluation results
- Mean Reward on CartPole-v1self-reported500.000
- Standard Deviation on CartPole-v1self-reported0.000
- Certification Score on CartPole-v1self-reported500.000