Closed-loop deep learning: generating forward models with back-propagation

01/09/2020
by   Sama Daryanavard, et al.
19

A reflex is a simple closed loop control approach which tries to minimise an error but fails to do so because it will always react too late. An adaptive algorithm can use this error to learn a forward model with the help of predictive cues. For example a driver learns to improve their steering by looking ahead to avoid steering in the last minute. In order to process complex cues such as the road ahead deep learning is a natural choice. However, this is usually only achieved indirectly by employing deep reinforcement learning having a discrete state space. Here, we show how this can be directly achieved by embedding deep learning into a closed loop system and preserving its continuous processing. We show specifically how error back-propagation can be achieved in z-space and in general how gradient based approaches can be analysed in such closed loop scenarios. The performance of this learning paradigm is demonstrated using a line-follower both in simulation and on a real robot that show very fast and continuous learning.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 6

page 7

page 9

page 12

research
09/07/2023

Prime and Modulate Learning: Generation of forward models with signed back-propagation and environmental cues

Deep neural networks employing error back-propagation for learning can s...
research
02/08/2015

From Pixels to Torques: Policy Learning with Deep Dynamical Models

Data-efficient learning in continuous state-action spaces using very hig...
research
10/08/2015

Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models

Data-efficient reinforcement learning (RL) in continuous state-action sp...
research
01/22/2023

Deep Reinforcement Learning for Concentric Tube Robot Path Planning

As surgical interventions trend towards minimally invasive approaches, C...
research
04/15/2023

A novel approach of a deep reinforcement learning based motion cueing algorithm for vehicle driving simulation

In the field of motion simulation, the level of immersion strongly depen...
research
04/11/2016

A statistical learning strategy for closed-loop control of fluid flows

This work discusses a closed-loop control strategy for complex systems u...
research
05/02/2013

Deep Learning of Representations: Looking Forward

Deep learning research aims at discovering learning algorithms that disc...

Please sign up or login with your details

Forgot password? Click here to reset