top of page

Project Goal

 

Train an agent in RoboCup to learn skills that enable it to score goals past a goalkeeper. 


Project steps
 

  • Read the Deep Robocup paper which doesn't use skills and cannot score past a goalkeeper.

  • Understand the DQN HFO framework

  • Incorporate changes to enable the agent to learn skills

  • Compare the performance with the original Deep RoboCup paper

 

Required knowledge

 

  • Random Signals.

  • Any knowledge in machine learning (DL, RL, t-SNE) is an advantage.

 

Environment

  • C++/python (RoboCup)

  • Caffe

  • Torch

 

Comments and links

 

 

 

Learning to play RoboCup soccer from scratch

using Deep Learning

Department of Electrical Engineering          Technion - Israel Institute of Technology
Control Robotics and Machine Learning Lab- המעבדה לבקרה רובוטיקה ולמידה חישובית

Background

 

RoboCup is a soccer platform that has been used as a testbed for developing Artificial Intelligence algorithms for soccer playing robots. The goal is to have a team of robots that play against the soccer world champions in 2050!

Our goal is to teach an agent to play soccer from scratch. That is, place an agent on a soccer field with a goalkeeper and try and teach him the basic skills which include (1) Approaching the ball, (2) Dribbling to the goalkeeper and (3) scoring past a goalkeeper.

bottom of page