Modeling a Continuous Locomotion Behavior of an Intelligent Agent Using Deep Reinforcement Technique

Dankwa, Stephen; Zheng, Wenfeng

doi:10.1109/ccet48361.2019.8989177

Cited by 13 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper mainly studies the performance of LSTM [33,34,35,36,37] and its improved network [38,39] in text value classification. The input of the LSTM network was a word vector, the collected movie comment data was pre-processed to get the word vector in the dataset.…”

Section: Methodsmentioning

confidence: 99%

Increasing Text Filtering Accuracy with Improved LSTM

Dang,

Cai,

Liu

et al. 2023

cai

View full text Add to dashboard Cite

How to eliminate useless information in the vast network information and retain effective information is a problem that needs to be continuously explored in the field of deep learning. This paper conducts text classification on the network evaluation frequently encountered in daily life, mainly to screen out the meaningless comments published by Internet users, to have access to more useful information. In this paper, a text filtering model was constructed based on word vector and Long Short-Term Memory (LSTM) and improved by adding Deep Averaging Networks (DAN) and convolutional neural network (CNN). The major improvement of the LSTM & DAN model was to retain the original word vector information and to improve the accuracy of the text classification model without increasing hyperparameter and model structure complexity. The LSTM & CNN model mainly combines the advantages of convolutional neural network in exploring the deep information of text, which was an improvement over the original LSTM. It was proved by experiments that this improvement is meaningful. Compared with the shallow neural network, the accuracy has been greatly improved.

show abstract

Section: Methodsmentioning

confidence: 99%

Increasing Text Filtering Accuracy with Improved LSTM

Dang,

Cai,

Liu

et al. 2023

cai

View full text Add to dashboard Cite

show abstract

“…Of the families of RL algorithms, we used the policy gradient method, which optimizes the performance of the expected cumulative reward by finding a good parametrized neural network policy. The chosen algorithm is the Tower crane-based 3D printing twin-delayed deep deterministic policy gradient (TD3; Grondman et al, 2012;Konda and Tsitsiklis, 1999), an RL method suitable for models characterized by continuous action spaces (Dankwa and Zheng, 2019). The TD3 is an actor-critic architecture that consists of two parts: an actor and a critic.…”

Section: Agent Modelling and Learning Algorithmmentioning

confidence: 99%

A new concept for large additive manufacturing in construction: tower crane-based 3D printing controlled by deep reinforcement learning

Parisi

Sangiorgio

Parisi

et al. 2023

View full text Add to dashboard Cite

Purpose Most of the 3D printing machines do not comply with the requirements of on-site, large-scale multi-story building construction. This paper aims to propose the conceptualization of a tower crane (TC)-based 3D printing controlled by artificial intelligence (AI) as the first step towards a large 3D printing development for multi-story buildings. It also aims to overcome the most important limitation of additive manufacturing in the construction industry (the build volume) by exploiting the most important machine used in the field: TCs. It assesses the technology feasibility by investigating the accuracy reached in the printing process. Design/methodology/approach The research is composed of three main steps: firstly, the TC-based 3D printing concept is defined by proposing an aero-pendulum extruder stabilized by propellers to control the trajectory during the extrusion process; secondly, an AI-based system is defined to control both the crane and the extruder toolpath by exploiting deep reinforcement learning (DRL) control approach; thirdly the proposed framework is validated by simulating the dynamical system and analysing its performance. Findings The TC-based 3D printer can be effectively used for additive manufacturing in the construction industry. Both the TC and its extruder can be properly controlled by an AI-based control system. The paper shows the effectiveness of the aero-pendulum extruder controlled by AI demonstrated by simulations and validation. The AI-based control system allows for reaching an acceptable tolerance with respect to the ideal trajectory compared with the system tolerance without stabilization. Originality/value In related literature, scientific investigations concerning the use of crane systems for 3D printing and AI-based systems for control are completely missing. To the best of the authors’ knowledge, the proposed research demonstrates for the first time the effectiveness of this technology conceptualized and controlled with an intelligent DRL agent. Practical implications The results provide the first step towards the development of a new additive manufacturing system for multi-storey constructions exploiting the TC-based 3D printing. The demonstration of the conceptualization feasibility and the control system opens up new possibilities to activate experimental research for companies and research centres.

show abstract

“…RL algorithms characterized as off‐policy generally utilized a separate behaviour policy which is independent of the policy which is being improved upon. The key advantage of the separation is that the behaviour policy can operate by sampling all actions, while the estimation policy can be deterministic [61]. TD3 was built on the DDPG algorithm to increase stability and performance with consideration of function approximation error [60].…”

Section: Dynamic Power Allocation With Drlmentioning

confidence: 99%

“…In order to reduce overestimation bias problems, the authors in [60] extended DDPG to twin delayed deep deterministic policy gradient algorithm (TD3), which estimates the target Q value by using the minimum of two target Q value, called clipped double Q learning. DPG and DDPG algorithms paved way to TD3 algorithms by the successful works on DQN [60, 61]. TD3 adopts two critics to get a less optimistic estimate of an action value by taking the minimum between two estimates.…”

Section: Related Workmentioning

confidence: 99%

Multi‐agent deep reinforcement learning‐based energy efficient power allocation in downlink MIMO‐NOMA systems

Jo¹,

Jong²,

Pak³

et al. 2021

IET Communications

View full text Add to dashboard Cite

NOMA and MIMO are considered to be the promising technologies to meet huge access demands and high data rate requirements of 5G wireless networks. In this paper, the power allocation problem in a downlink MIMO-NOMA system to maximize the energy efficiency while ensuring the quality-of-service of all users is investigated. Two deep reinforcement learning-based frameworks are proposed to solve this non-convex and dynamic optimization problem, referred to as the multi-agent DDPG/TD3-based power allocation framework. In particular, with current channel conditions as input, every single agent of two multi-agent frameworks dynamically outputs the optimum power allocation policy for all users in every cluster by DDPG/TD3 algorithm, and the additional actor network is also added to the conventional multi-agent model in order to adjust power volumes allocated to clusters to improve overall performance of the system. Finally, both frameworks adjust the entire power allocation policy by updating the weights of neural networks according to the feedback of the system. Simulation results show that the proposed multi-agent deep reinforcement learning based power allocation frameworks can significantly improve the energy efficiency of the MIMO-NOMA system under various transmit power limitations and minimum data rates compared with other approaches, including the performance comparison over MIMO-OMA.

show abstract

Modeling a Continuous Locomotion Behavior of an Intelligent Agent Using Deep Reinforcement Technique

Cited by 13 publications

References 1 publication

Increasing Text Filtering Accuracy with Improved LSTM

Increasing Text Filtering Accuracy with Improved LSTM

A new concept for large additive manufacturing in construction: tower crane-based 3D printing controlled by deep reinforcement learning

Multi‐agent deep reinforcement learning‐based energy efficient power allocation in downlink MIMO‐NOMA systems

Contact Info

Product

Resources

About