Reinforcement Learning with Convolutional Reservoir Computing

12/05/2019
by   Hanten Chang, et al.
0

Recently, reinforcement learning models have achieved great success, mastering complex tasks such as Go and other games with higher scores than human players. Many of these models store considerable data on the tasks and achieve high performance by extracting visual and time-series features using convolutional neural networks (CNNs) and recurrent neural networks, respectively. However, these networks have very high computational costs because they need to be trained by repeatedly using the stored data. In this study, we propose a novel practical approach called reinforcement learning with convolutional reservoir computing (RCRC) model. The RCRC model uses a fixed random-weight CNN and a reservoir computing model to extract visual and time-series features. Using these extracted features, it decides actions with an evolution strategy method. Thereby, the RCRC model has several desirable features: (1) there is no need to train the feature extractor, (2) there is no need to store training data, (3) it can take a wide range of actions, and (4) there is only a single task-dependent weight parameter to be trained. Furthermore, we show the RCRC model can solve multiple reinforcement learning tasks with a completely identical feature extractor.

READ FULL TEXT

page 5

page 6

research
07/18/2019

Convolutional Reservoir Computing for World Models

Recently, reinforcement learning models have achieved great success, com...
research
04/27/2020

Adaptive model selection in photonic reservoir computing by reinforcement learning

Photonic reservoir computing is an emergent technology toward beyond-Neu...
research
03/21/2018

Reservoir computing approaches for representation and classification of multivariate time series

Classification of multivariate time series (MTS) has been tackled with a...
research
03/03/2022

Deep Q-network using reservoir computing with multi-layered readout

Recurrent neural network (RNN) based reinforcement learning (RL) is used...
research
01/14/2021

Unveiling the role of plasticity rules in reservoir computing

Reservoir Computing (RC) is an appealing approach in Machine Learning th...
research
09/13/2023

Efficient quantum recurrent reinforcement learning via quantum reservoir computing

Quantum reinforcement learning (QRL) has emerged as a framework to solve...
research
05/07/2017

DropIn: Making Reservoir Computing Neural Networks Robust to Missing Inputs by Dropout

The paper presents a novel, principled approach to train recurrent neura...

Please sign up or login with your details

Forgot password? Click here to reset