SnEhAh018/q-Taxi-v3

Q-Learning Agent playing Taxi-v3

This is a trained model of a Q-Learning agent playing Taxi-v3.

Evaluation

• Environment: Taxi-v3
• Mean reward: 7.56
• Standard deviation: 2.71
• Leaderboard score (mean_reward - std_reward): 4.8533
• Required course score: 4.5
• Evaluation episodes: 100

Training configuration

• Training episodes: 25000
• Learning rate: 0.7
• Gamma: 0.95
• Maximum steps: 99
• Maximum epsilon: 1.0
• Minimum epsilon: 0.05
• Epsilon decay rate: 0.005
• Q-table shape: (500, 6)

Model files

• q-learning.pkl — trained Q-table and configuration
• results.json — evaluation results
• taxi-replay.mp4 — recorded agent replay

This model was created as part of the Hugging Face Deep Reinforcement Learning Course Unit 2 hands-on.