Disentangling Controllable Object through Video Prediction Improves Visual Reinforcement Learning

In many vision-based reinforcement learning (RL) problems, the agent controls a movable object in its visual field, e.g., the player's avatar in video games and the robotic arm in visual grasping and manipulation. Leveraging action-conditioned video prediction, we propose an end-to-end learning...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-02
Main Authors: Zhong, Yuanyi, Schwing, Alexander, Peng, Jian
Format: Article
Language:English
Subjects:
Algorithms
Computer & video games
Grasping (robotics)
Learning
Reagents
Robot arms
Stability
Visual fields
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In many vision-based reinforcement learning (RL) problems, the agent controls a movable object in its visual field, e.g., the player's avatar in video games and the robotic arm in visual grasping and manipulation. Leveraging action-conditioned video prediction, we propose an end-to-end learning framework to disentangle the controllable object from the observation signal. The disentangled representation is shown to be useful for RL as additional observation channels to the agent. Experiments on a set of Atari games with the popular Double DQN algorithm demonstrate improved sample efficiency and game performance (from 222.8% to 261.4% measured in normalized game scores, with prediction bonus reward).
ISSN:2331-8422