首页
学习
活动
专区
工具
TVP
发布
社区首页 >专栏 >强化学习中的光流 运动感知

强化学习中的光流 运动感知

作者头像
用户1908973
发布2019-05-15 16:01:10
4550
发布2019-05-15 16:01:10
举报
文章被收录于专栏:CreateAMindCreateAMind
Motion Perception in Reinforcement Learning with Dynamic Objects

Artemij Amiranashvili1 Alexey Dosovitskiy2 Vladlen Koltun2 Thomas Brox1

1University of Freiburg 2Intel Labs

Abstract

In dynamic environments, learned controllers are supposed to take motion into account when selecting the action to be taken. However, in existing reinforcement learning works motion is rarely treated explicitly; it is rather assumed that the controller learns the necessary motion representation from temporal stacks of frames implicitly. In this paper, we show that for continuous control tasks learning an explicit representation of motion clearly improves the quality of the learned controller in dynamic scenarios. We demonstrate this on common benchmark tasks (Walker, Swimmer, Hopper), on target reaching and ball catching tasks with simulated robotic arms, and on a dynamic single ball juggling task. Moreover, we find that when equipped with an appropriate network architecture, the agent can, on some tasks, learn motion features also with pure reinforcement learning, without additional supervision.

https://lmb.informatik.uni-freiburg.de/projects/flowrl/

https://github.com/lmb-freiburg/flow_rl

本文参与 腾讯云自媒体分享计划,分享自微信公众号。
原始发表:2019-05-05,如有侵权请联系 cloudcommunity@tencent.com 删除

本文分享自 CreateAMind 微信公众号,前往查看

如有侵权,请联系 cloudcommunity@tencent.com 删除。

本文参与 腾讯云自媒体分享计划  ,欢迎热爱写作的你一起参与!

评论
登录后参与评论
0 条评论
热度
最新
推荐阅读
目录
  • Motion Perception in Reinforcement Learning with Dynamic Objects
    • Abstract
    领券
    问题归档专栏文章快讯文章归档关键词归档开发者手册归档开发者手册 Section 归档