cartmanishere / self-learning-bot

A line follower bot which uses a Reinforcement Learning algorithm to learn to follow the line

Self-Learning-Robot

Q Learning is a model-free reinforcement learning algorithm. The goal of Q-learning is to learn a policy, which tells an agent what action to take under what circumstances.

A bot is made with Raspberry Pi Controller with IR sensors to be used as a Reinforcement Learning agent.

This project was inspired by - An introduction to Reinforcement Learning

Our Approach

Our goal is to make this agent learn the policy to follow a line (detected by its sensors) by learning from its own mistakes. We do not explicitly provide any instructions to the bot. We only provide a free environment for the agent to interact and the environment will present reward for each action of the agent.

Contributors

1. Pranav Gajjewar
2. Omkar Thawakar

Result