🚖 Taxi-v3 Q-Learning Agent
This repository contains a trained Q-learning agent for the Taxi-v3 environment.
The agent learns to efficiently pick up and drop off passengers while maximizing reward using a tabular Q-learning approach.
The trained model is packaged as model.zip, which contains the learned q_table.npy.
📌 Environment Details
- Environment:
Taxi-v3 - Algorithm: Q-learning (Tabular RL)
- State Space: 500 discrete states
- Action Space: 6 discrete actions
- Training Episodes: 20,000+
- Framework: OpenAI Gym / Gymnasium compatible
📦 Model File
The trained agent is stored as: