14613

From Pixels to Torques: Policy Learning using Deep Dynamical Convolutional Networks

John-Alexander M. Assael
Imperial College London, Department of Computing
Imperial College London, 2015

@article{assael2015pixels,

   title={From Pixels to Torques: Policy Learning using Deep Dynamical Convolutional Networks},

   author={Assael, John-Alexander M},

   year={2015}

}

Data-efficient learning in continuous state-action spaces using high-dimensional observations remains an elusive challenge in developing fully autonomous systems. An instance of this challenge is the pixels to torques problem, which identifies key elements of an autonomous agent: autonomous thinking and decision making using sensor measurements only, learning from mistakes, and applying past experiences to novel situations. In this research, we introduce a deep dynamical convolutional model, able to learn complex non-linear dynamics and do long-term predictions. Compared to state-of-the-art reinforcement learning methods for continuous state and action space problems, our approach is solid and efficient as it is model-based, is scalable to high-dimensional state spaces, learns quickly, and is a major step towards fully autonomous learning from pixels to torques.
VN:F [1.9.22_1171]
Rating: 5.0/5 (1 vote cast)
From Pixels to Torques: Policy Learning using Deep Dynamical Convolutional Networks, 5.0 out of 5 based on 1 rating

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: