Deep Reinforcement Learning From Raw Pixels in Doom

10/07/2016
by   Danijar Hafner, et al.
0

Using current reinforcement learning methods, it has recently become possible to learn to play unknown 3D games from raw pixels. In this work, we study the challenges that arise in such complex environments, and summarize current methods to approach these. We choose a task within the Doom game, that has not been approached yet. The goal for the agent is to fight enemies in a 3D world consisting of five rooms. We train the DQN and LSTM-A3C algorithms on this task. Results show that both algorithms learn sensible policies, but fail to achieve high scores given the amount of training. We provide insights into the learned behavior, which can serve as a valuable starting point for further research in the Doom domain.

READ FULL TEXT

page 26

page 27

research
09/18/2016

Playing FPS Games with Deep Reinforcement Learning

Advances in deep reinforcement learning have allowed autonomous agents t...
research
10/19/2022

DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation

The recent advances in reinforcement learning have led to effective meth...
research
09/10/2019

Reinforcement Learning and Video Games

Reinforcement learning has exceeded human-level performance in game play...
research
03/31/2017

Learning Visual Servoing with Deep Features and Fitted Q-Iteration

Visual servoing involves choosing actions that move a robot in response ...
research
01/06/2018

Using reinforcement learning to learn how to play text-based games

The ability to learn optimal control policies in systems where action sp...
research
12/01/2016

Playing Doom with SLAM-Augmented Deep Reinforcement Learning

A number of recent approaches to policy learning in 2D game domains have...
research
05/31/2018

Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation

Deep Reinforcement Learning has managed to achieve state-of-the-art resu...

Please sign up or login with your details

Forgot password? Click here to reset