q-Taxi-v3

This model was trained as part of the Hugging Face Deep Reinforcement Learning Course.

Model Description

• Environment: Taxi-v3
• Library: q-learning
• Algorithm: q-learning
• Mean Reward: 8.00 +/- 0.50

Evaluation Results

The model was evaluated on Taxi-v3 and achieved an average reward of 8.00 with a standard deviation of 0.50.