johith9381/q-Taxi-v3

Q-Learning Agent playing Taxi-v3

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

Training

• Algorithm: Q-Learning
• Environment: Taxi-v3
• Training episodes: 25,000
• Learning rate: 0.7
• Discount factor: 0.95
• Maximum steps: 99
• Maximum epsilon: 1.0
• Minimum epsilon: 0.05
• Epsilon decay rate: 0.005

Evaluation

Mean reward: 7.52 +/- 2.73

Certification score:

7.52 - 2.73 = 4.79

Required score: 4.5

Model

The trained Q-table is stored in q-learning.pkl.