Abstract
We present a novel intrinsically motivated agent that learns how to control the environment in the fastest possible manner by optimizing learning progress. It learns what can be controlled, how to allocate time and attention, and the relations between objects using surprise based motivation. The effectiveness of our method is demonstrated in a synthetic as well as a robotic manipulation environment yielding considerably improved performance and smaller sample complexity. In a nutshell, our work combines several task-level planning agent structures (backtracking search on task graph, probabilistic road-maps, allocation of search efforts) with intrinsic motivation to achieve learning from scratch.
Media
Videos
Poster
Additional Information
Links
BibTex
@inproceedings{BlaesVlastelicaZhuMartius2019:CWYC,
title = {Control {W}hat {Y}ou {C}an: {I}ntrinsically Motivated Task-Planning Agent},
author = {Blaes, Sebastian and Vlastelica, Marin and Zhu, Jia-Jie and Martius, Georg},
booktitle = {Advances in Neural Information Processing (NeurIPS'19)},
pages = {12520--12531},
publisher = {Curran Associates, Inc.},
year = {2019},
url = {http://papers.nips.cc/paper/9418-control-what-you-can-intrinsically-motivated-task-planning-agent.pdf}
} }
title = {Control {W}hat {Y}ou {C}an: {I}ntrinsically Motivated Task-Planning Agent},
author = {Blaes, Sebastian and Vlastelica, Marin and Zhu, Jia-Jie and Martius, Georg},
booktitle = {Advances in Neural Information Processing (NeurIPS'19)},
pages = {12520--12531},
publisher = {Curran Associates, Inc.},
year = {2019},
url = {http://papers.nips.cc/paper/9418-control-what-you-can-intrinsically-motivated-task-planning-agent.pdf}
} }