Reinforce Agent playing CartPole-v1
REINFORCE agent trained as part of the Hugging Face Deep Reinforcement Learning Course Unit 4.
Evaluation
- Mean reward: 492.30
- Standard deviation: 20.28
- Unit 4 score (mean - std): 472.02
Hyperparameters
- Hidden size: 64
- Training episodes: 3000
- Evaluation episodes: 10
- Maximum steps: 500
- Gamma: 0.99
- Learning rate: 0.01
Evaluation results
- mean_reward on CartPole-v1self-reported492.30 +/- 20.28