Skip to content

README.md

Latest commit

 

History

History
27 lines (14 loc) · 927 Bytes

README.md

File metadata and controls

27 lines (14 loc) · 927 Bytes
Raw

DRL-Behavioral-Cloning-Imitation-Learning

This repository contains implementations of imitation learning techniques, specifically behavioral cloning and DAgger (Dataset Aggregation), applied to the CarRacing-v2 environment.

Overview

Imitation learning is a type of machine learning where an agent learns to perform tasks by observing expert demonstrations. The goal of this project is to teach an AI to navigate a racing track by imitating an expert's behavior.

Files

  • main.ipynb: Jupyter Notebook containing the main code for training and evaluating the model.
  • model.onnx: The trained model in ONNX format.

Getting Started

  1. Clone this repository:

bash git clone https://github.com/d3rar/DRL-Behavioral-Cloning-imitation-learning.git

  1. Navigate to the project directory:

bash cd DRL-Behavioral-Cloning-imitation-learning

  1. Open the Jupyter Notebook:

bash jupyter notebook main.ipynb