HFO-DQN

Playing 2D RoboCup with Deep Reinforcement Learning

Latest Results

After long months of work on construction of our interface and on bringing the system up to speed, in the past few weeks we have been...

Background

Reinforcement Learning: A reinforcement learning agent attempts to learn a policy π : S → A by maximizing the reward it receives in...

OVERVIEW

Playing RoboCup with Deep Reinforcement Learning

HFO-DQN is an undergraduate project at the Andrew Viterbi Electrical Engineering Faculty, Technion, Israel Institute of Technology.

It was created by Yona Cohen and Orr Krupnik, under the supervision of Daniel Mankowitz and Tom Zahavy at Shie Mannor's research group. Read more about the project on the Introduction page.

HFO-DQN

Playing 2D RoboCup with Deep Reinforcement Learning

OVERVIEW

RECENT POSTS

Sign Up

AND STAY UPDATED!