An Experimental Study for Exploration-oriented Behavior in Maze-solving using Reinforcement Learning based on Communication Protocol

2019 ◽  
Vol 9 (2) ◽  
pp. 31-37
Author(s):  
Masashi SUGIMOTO ◽  
Shunsuke INADA ◽  
Haruka MATSUFUJI ◽  
Shiro URUSHIHARA ◽  
Kazunori HOSOTANI ◽  
...  
Keyword(s):  
Experimental Study ◽  
Reinforcement Learning ◽  
Communication Protocol

scholarly journals An Edge Based Multi-Agent Auto Communication Method for Traffic Light Control

Sensors ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 4291 ◽  
Author(s):  
Qiang Wu ◽  
Jianqing Wu ◽  
Jun Shen ◽  
Binbin Yong ◽  
Qingguo Zhou
Keyword(s):  
Reinforcement Learning ◽  
Control Method ◽  
Communication Protocol ◽  
Traffic Signal ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Light Control ◽  
Traffic Light ◽  
Traffic Light Control ◽  
Multi Agent

With smart city infrastructures growing, the Internet of Things (IoT) has been widely used in the intelligent transportation systems (ITS). The traditional adaptive traffic signal control method based on reinforcement learning (RL) has expanded from one intersection to multiple intersections. In this paper, we propose a multi-agent auto communication (MAAC) algorithm, which is an innovative adaptive global traffic light control method based on multi-agent reinforcement learning (MARL) and an auto communication protocol in edge computing architecture. The MAAC algorithm combines multi-agent auto communication protocol with MARL, allowing an agent to communicate the learned strategies with others for achieving global optimization in traffic signal control. In addition, we present a practicable edge computing architecture for industrial deployment on IoT, considering the limitations of the capabilities of network transmission bandwidth. We demonstrate that our algorithm outperforms other methods over 17% in experiments in a real traffic simulation environment.

scholarly journals A study on handling intrinsic motivation for devising sample efficient actor-critic agents

2021 ◽  
Author(s):  
André Quadros ◽  
Roberto Xavier Junior ◽  
Kleber Souza ◽  
Bruno Gomes ◽  
Filipe Saraiva ◽  
...  
Keyword(s):  
Machine Learning ◽  
Experimental Study ◽  
Reinforcement Learning ◽  
Intrinsic Motivation ◽  
Sampling Efficiency ◽  
Practical Guidelines

Reinforcement learning has evolved in recent years,and overcoming challenges found in this field. This area, unlikeconventional machine learning, does not learn through a setof observational instances, but through interaction with anenvironment. The sampling efficiency of a reinforcement learningagent is a challenge. That is, how to make an agent learn withinan environment with as little interaction as possible. In this workwe perform an experimental study on the difficulties to integratea strategy of intrinsic motivation to an actor-critic agent toimprove the sampling efficiency. We found results that point to theeffectiveness of the intrinsic motivation as a approach to improvethe agent’s sampling efficiency, as well as its performance. Weshare practical guidelines to assist in the implementation of actor-critic agents to deal with sparse reward environments whilemaking use of intrinsic motivation feedback.

scholarly journals An Experimental Study on State Representation Extraction for Vision-Based Deep Reinforcement Learning

2021 ◽  
Vol 11 (21) ◽  
pp. 10337
Author(s):  
Junkai Ren ◽  
Yujun Zeng ◽  
Sihang Zhou ◽  
Yichuan Zhang
Keyword(s):  
Experimental Study ◽  
Reinforcement Learning ◽  
Network Architecture ◽  
Representation Learning ◽  
Evaluation Metrics ◽  
High Dimensional ◽  
Regularization Methods ◽  
Challenging Problem ◽  
State Representation ◽  
Sample Quality

Scaling end-to-end learning to control robots with vision inputs is a challenging problem in the field of deep reinforcement learning (DRL). While achieving remarkable success in complex sequential tasks, vision-based DRL remains extremely data-inefficient, especially when dealing with high-dimensional pixels inputs. Many recent studies have tried to leverage state representation learning (SRL) to break through such a barrier. Some of them could even help the agent learn from pixels as efficiently as from states. Reproducing existing work, accurately judging the improvements offered by novel methods, and applying these approaches to new tasks are vital for sustaining this progress. However, the demands of these three aspects are seldom straightforward. Without significant criteria and tighter standardization of experimental reporting, it is difficult to determine whether improvements over the previous methods are meaningful. For this reason, we conducted ablation studies on hyperparameters, embedding network architecture, embedded dimension, regularization methods, sample quality and SRL methods to compare and analyze their effects on representation learning and reinforcement learning systematically. Three evaluation metrics are summarized, including five baseline algorithms (including both value-based and policy-based methods) and eight tasks are adopted to avoid the particularity of each experiment setting. We highlight the variability in reported methods and suggest guidelines to make future results in SRL more reproducible and stable based on a wide number of experimental analyses. We aim to spur discussion about how to assure continued progress in the field by minimizing wasted effort stemming from results that are non-reproducible and easily misinterpreted.

scholarly journals Route Selection for Multi-Hop Cognitive Radio Networks Using Reinforcement Learning: An Experimental Study

IEEE Access ◽  
2016 ◽  
Vol 4 ◽  
pp. 6304-6324 ◽  
Author(s):  
Aqeel Raza Syed ◽  
Kok-Lim Alvin Yau ◽  
Junaid Qadir ◽  
Hafizal Mohamad ◽  
Nordin Ramli ◽  
...  
Keyword(s):  
Experimental Study ◽  
Reinforcement Learning ◽  
Cognitive Radio ◽  
Cognitive Radio Networks ◽  
Radio Networks ◽  
Route Selection ◽  
Selection For
Sign in / Sign up

Export Citation Format

Share Document