herurg/q-Taxi-v3

Q-Learning Agent playing Taxi-v3

This is a trained Q-Learning agent for Hugging Face Deep Reinforcement Learning Course Unit 2.

Evaluation

• Environment: Taxi-v3
• Mean reward: 7.52
• Standard deviation: 2.73
• Result (mean_reward - std_reward): 4.79
• Required course result: 4.5
• Evaluation episodes: 100

Compatibility note

The Q-table was trained and evaluated with Taxi-v4 in the current Gymnasium release because Taxi-v3 is deprecated there.

The Hugging Face Deep RL Course identifier remains Taxi-v3.