The reinforcement learning of an autonomous agent, Case study: Taxi Game
No Thumbnail Available
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Reinforcement learning (RL) is a powerful machine learning technique that enables autonomous
agents to learn and make decisions by interacting with their environment. It is inspired by the
behavioural psychology concept of learning through trial-and-error, where an agent takes actions,
receives rewards or penalties, and adjusts its behaviour accordingly to achieve specific goals.
In this thesis, we focus on the mechanisms, techniques, and applications of this exciting discipline,
We apply the Q-learning algorithm wich is a reinforcement learning algorithm that seeks to
find the best possible next action given its current state, in order to maximise the reward it receives
from the enviroment Taxi game wich is one of many environments available on OpenAI Gym, The
aim of this algorithm is to make sure the taxi can get to the passenger, pick him up and bring him
to the drop-off location in the fastest way possible, The core concept of Q-learning revolves around
the notion of a Q-table, a data structure that stores the estimated values of taking a specific action
in a particular state. As the agent (taxi) interacts with the environment, it continuously updates the
Q-table based on the rewards it receives. This iterative process enables the agent to gradually learn
which actions lead to favorable outcomes and which ones should be avoided.