COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration

2019-05-22Code Available0· sign in to hype

Nicholas Watters, Loic Matthey, Matko Bosnjak, Christopher P. Burgess, Alexander Lerchner

Code Available — Be the first to reproduce this paper.

Code

github.com/deepmind/spriteworld
OfficialIn papernone★ 0
github.com/google-deepmind/spriteworld
none★ 0

Abstract

Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep reinforcement learning algorithms. Here we introduce a modular approach to addressing these challenges in a continuous control environment, without using hand-crafted or supervised information. Our Curious Object-Based seaRch Agent (COBRA) uses task-free intrinsically motivated exploration and unsupervised learning to build object-based models of its environment and action space. Subsequently, it can learn a variety of tasks through model-based search in very few steps and excel on structured hold-out tests of policy robustness.

Tasks

continuous-control Continuous Control Deep Reinforcement Learning Object Object Discovery reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration

Code

Abstract

Tasks

Reproductions