herurg/Reinforce-CartPole-v1

Reinforce Agent playing CartPole-v1

This is a trained Reinforce agent for Unit 4 of the Hugging Face Deep Reinforcement Learning Course.

Evaluation

• Environment: CartPole-v1
• Mean reward: 500.00
• Standard deviation: 0.00
• Course result: 500.00
• Required result: 350
• Evaluation episodes: 10

Training

• Algorithm: REINFORCE / Monte Carlo Policy Gradient
• Hidden layer: 16
• Gamma: 1.0
• Learning rate: 1e-2
• Training episodes: 1500