Action-Conditional Video Prediction using Deep Networks in Atari Games

07/31/2015
by   Junhyuk Oh, et al.
0

Motivated by vision-based reinforcement learning (RL) problems, in particular Atari games from the recent benchmark Aracade Learning Environment (ALE), we consider spatio-temporal prediction problems where future (image-)frames are dependent on control variables or actions as well as previous frames. While not composed of natural scenes, frames in Atari games are high-dimensional in size, can involve tens of objects with one or more objects being controlled by the actions directly and many other objects being influenced indirectly, can involve entry and departure of objects, and can involve deep partial observability. We propose and evaluate two deep neural network architectures that consist of encoding, action-conditional transformation, and decoding layers based on convolutional neural networks and recurrent neural networks. Experimental results show that the proposed architectures are able to generate visually-realistic frames that are also useful for control over approximately 100-step action-conditional futures in some games. To the best of our knowledge, this paper is the first to make and evaluate long-term predictions on high-dimensional video conditioned by control inputs.

READ FULL TEXT

page 16

page 17

page 18

page 19

page 23

page 24

page 25

page 26

research
05/08/2018

Low-Latency Human Action Recognition with Weighted Multi-Region Convolutional Neural Network

Spatio-temporal contexts are crucial in understanding human actions in v...
research
04/07/2017

Recurrent Environment Simulators

Models that can simulate how environments change in response to actions ...
research
12/09/2019

Transformer Based Reinforcement Learning For Games

Recent times have witnessed sharp improvements in reinforcement learning...
research
07/03/2017

Hashing Over Predicted Future Frames for Informed Exploration of Deep Reinforcement Learning

In reinforcement learning (RL) tasks, an efficient exploration mechanism...
research
02/21/2020

Disentangling Controllable Object through Video Prediction Improves Visual Reinforcement Learning

In many vision-based reinforcement learning (RL) problems, the agent con...
research
05/05/2017

Motion Prediction Under Multimodality with Conditional Stochastic Networks

Given a visual history, multiple future outcomes for a video scene are e...
research
05/17/2016

Deep Action Sequence Learning for Causal Shape Transformation

Deep learning became the method of choice in recent year for solving a w...

Please sign up or login with your details

Forgot password? Click here to reset