Worm-level Control through Search-based Reinforcement Learning

11/09/2017
by   Mathias Lechner, et al.
0

Through natural evolution, nervous systems of organisms formed near-optimal structures to express behavior. Here, we propose an effective way to create control agents, by re-purposing the function of biological neural circuit models, to govern similar real world applications. We model the tap-withdrawal (TW) neural circuit of the nematode, C. elegans, a circuit responsible for the worm's reflexive response to external mechanical touch stimulations, and learn its synaptic and neural parameters as a policy for controlling the inverted pendulum problem. For reconfiguration of the purpose of the TW neural circuit, we manipulate a search-based reinforcement learning. We show that our neural policy performs as good as existing traditional control theory and machine learning approaches. A video demonstration of the performance of our method can be accessed at <https://youtu.be/o-Ia5IVyff8>.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/22/2018

Neuronal Circuit Policies

We propose an effective way to create interpretable control agents, by r...
research
09/11/2018

Re-purposing Compact Neuronal Circuit Policies to Govern Reinforcement Learning Tasks

We propose an effective method for creating interpretable control agents...
research
12/02/2022

Selecting Mechanical Parameters of a Monopode Jumping System with Reinforcement Learning

Legged systems have many advantages when compared to their wheeled count...
research
03/30/2021

Reinforcement learning for optimization of variational quantum circuit architectures

The study of Variational Quantum Eigensolvers (VQEs) has been in the spo...
research
08/16/2021

Introduction to Quantum Reinforcement Learning: Theory and PennyLane-based Implementation

The emergence of quantum computing enables for researchers to apply quan...
research
11/16/2020

Analog Circuit Design with Dyna-Style Reinforcement Learning

In this work, we present a learning based approach to analog circuit des...
research
10/08/2021

Ranking Cost: Building An Efficient and Scalable Circuit Routing Planner with Evolution-Based Optimization

Circuit routing has been a historically challenging problem in designing...

Please sign up or login with your details

Forgot password? Click here to reset