2018-10-23-amiranashvili18a.md

title	abstract	keywords	layout	series	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	publisher	container-title	volume	genre	issued	pdf	extras
Motion Perception in Reinforcement Learning with Dynamic Objects	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.	Reinforcement learning, Motion perception, Optical flow	inproceedings	Proceedings of Machine Learning Research	amiranashvili18a	0	Motion Perception in Reinforcement Learning with Dynamic Objects	156	168	156-168	156	false	Amiranashvili, Artemij and Dosovitskiy, Alexey and Koltun, Vladlen and Brox, Thomas	given family Artemij Amiranashvili given family Alexey Dosovitskiy given family Vladlen Koltun given family Thomas Brox	2018-10-23		PMLR	Proceedings of The 2nd Conference on Robot Learning	87	inproceedings	date-parts 2018 10 23	http://proceedings.mlr.press/v87/amiranashvili18a/amiranashvili18a.pdf	label link Supplementary video https://youtu.be/YALmehmmu3Q label link Source code https://github.com/lmb-freiburg/flow_rl