Search results for: hierarchical reinforcement learning

Authors: Adrian Millea

Abstract:

In hierarchical reinforcement learning, one of the main issues encountered is the discovery of subgoal states or options (which are policies reaching subgoal states) by partitioning the environment in a meaningful way. This partitioning usually requires an expensive global clustering operation or eigendecomposition of the Laplacian of the states graph. We propose a local solution to this issue, much more efficient than algorithms using global information, which successfully discovers subgoal states by computing a simple function, which we call heterogeneity for each state as a function of its neighbors. Moreover, we construct a value function using the difference in heterogeneity from one step to the next, as reward, such that we are able to explore the state space much more efficiently than say epsilon-greedy. The same principle can then be applied to higher level of the hierarchy, where now states are subgoals discovered at the level below.

Keywords: exploration, hierarchical reinforcement learning, locality, options, value functions

Procedia PDF Downloads 133

Authors: Fabio Fabris, Alex A. Freitas

Abstract:

Hierarchical classification is a special type of classification task where the class labels are organised into a hierarchy, with more generic class labels being ancestors of more specific ones. Meta-learning for classification-algorithm recommendation consists of recommending to the user a classification algorithm, from a pool of candidate algorithms, for a dataset, based on the past performance of the candidate algorithms in other datasets. Meta-learning is normally used in conventional, non-hierarchical classification. By contrast, this paper proposes a meta-learning approach for more challenging task of hierarchical classification, and evaluates it in a large number of bioinformatics datasets. Hierarchical classification is especially relevant for bioinformatics problems, as protein and gene functions tend to be organised into a hierarchy of class labels. This work proposes meta-learning approach for recommending the best hierarchical classification algorithm to a hierarchical classification dataset. This work’s contributions are: 1) proposing an algorithm for splitting hierarchical datasets into new datasets to increase the number of meta-instances, 2) proposing meta-features for hierarchical classification, and 3) interpreting decision-tree meta-models for hierarchical classification algorithm recommendation.

Keywords: algorithm recommendation, meta-learning, bioinformatics, hierarchical classification

Procedia PDF Downloads 279

Authors: Mahasa Zahirnia

Abstract:

The purpose of this paper is to explore new and effective ways of optimizing satellite images using artificial intelligence, and the process of implementing reinforcement learning to enhance the quality of data captured within the image. In our implementation of Bellman's Reinforcement Learning equations, associated state diagrams, and multi-stage image processing, we were able to enhance image quality, detect and define objects. Reinforcement learning is the differentiator in the area of artificial intelligence, and Q-Learning relies on trial and error to achieve its goals. The reward system that is embedded in Q-Learning allows the agent to self-evaluate its performance and decide on the best possible course of action based on the current and future environment. Results show that within a simulated environment, built on the images that are commercially available, the rate of detection was 40-90%. Reinforcement learning through Q-Learning algorithm is not just desired but required design criteria for image optimization and enhancements. The proposed methods presented are a cost effective method of resolving uncertainty of the data because reinforcement learning finds ideal policies to manage the process using a smaller sample of images.

Keywords: Q-learning, image optimization, reinforcement learning, Markov decision process

Procedia PDF Downloads 182

Authors: Jawairia Rasheed

Abstract:

Modern robots are often used for search and rescue purpose. One of the key areas of interest in such cases is learning complex environments. One of the key methodologies for robots in such cases is reinforcement learning. In reinforcement learning robots learn to move the path to reach the goal while avoiding obstacles. Q-learning, one of the most advancement of reinforcement learning is used for making the robots to learn the path. Robots learn by interacting with the environment to reach the goal. In this paper simulation model of bee-like robots is implemented in NETLOGO. In the start the learning rate was less and it increased with the passage of time. The bees successfully learned to reach the goal while avoiding obstacles through Q-learning technique.

Keywords: reinforlearning of bee like robots for reaching the goalcement learning for randomly placed obstacles, obstacle avoidance through q-learning, q-learning for obstacle avoidance,

Procedia PDF Downloads 62

Authors: Edward W. Staley, Corban G. Rivera, Ashley J. Llorens

Abstract:

Advances in reinforcement learning (RL) have resulted in recent breakthroughs in the application of artificial intelligence (AI) across many different domains. An emerging landscape of development environments is making powerful RL techniques more accessible for a growing community of researchers. However, most existing frameworks do not directly address the problem of learning in complex operating environments, such as dense urban settings or defense-related scenarios, that incorporate distributed, heterogeneous teams of agents. To help enable AI research for this important class of applications, we introduce the AI Arena: a scalable framework with flexible abstractions for distributed multi-agent reinforcement learning. The AI Arena extends the OpenAI Gym interface to allow greater flexibility in learning control policies across multiple agents with heterogeneous learning strategies and localized views of the environment. To illustrate the utility of our framework, we present experimental results that demonstrate performance gains due to a distributed multi-agent learning approach over commonly-used RL techniques in several different learning environments.

Keywords: reinforcement learning, multi-agent, deep learning, artificial intelligence

Procedia PDF Downloads 131

Authors: Hyeongbok Kim, Lingling Zhao, Xiaohong Su

Abstract:

Deep reinforcement learning has been applied to address various problems in robotics, such as autonomous driving and unmanned aerial vehicle. However, because of the sparse reward penalty for a collision with obstacles during the navigation mission, the agent fails to learn the optimal policy or requires a long time for convergence. Therefore, using obstacles and enemy agents, in this paper, we present a curriculum-based boost learning method to effectively train compound skills during multi-agent reinforcement learning. First, to enable the agents to solve challenging tasks, we gradually increased learning difficulties by adjusting reward shaping instead of constructing different learning environments. Then, in a benchmark environment with static obstacles and moving enemy agents, the experimental results showed that the proposed curriculum learning strategy enhanced cooperative navigation and compound collision avoidance skills in uncertain environments while improving learning efficiency.

Keywords: curriculum learning, hard exploration, multi-agent reinforcement learning, robotic navigation, sparse reward

Procedia PDF Downloads 62

Authors: Khalil Bachiri, Ali Yahyaouy, Nicoleta Rogovschi

Abstract:

Improved user experience is a goal of contemporary recommender systems. Recommender systems are starting to incorporate reinforcement learning since it easily satisfies this goal of increasing a user’s reward every session. In this paper, we examine the most effective Reinforcement Learning agent tactics on the Movielens (1M) dataset, balancing precision and a variety of recommendations. The absence of variability in final predictions makes simplistic techniques, although able to optimize ranking quality criteria, worthless for consumers of the recommendation system. Utilizing the stochasticity of Leonard-Ornstein processes, our suggested strategy encourages the agent to investigate its surroundings. Research demonstrates that raising the NDCG (Discounted Cumulative Gain) and HR (HitRate) criterion without lowering the Ornstein-Uhlenbeck process drift coefficient enhances the diversity of suggestions.

Keywords: recommender systems, reinforcement learning, deep learning, DDPG, Leonard-Ornstein process

Procedia PDF Downloads 101

Authors: Z. Abdullah, A. R. Hamdan

Abstract:

Clustering is a process of grouping objects and data into groups of clusters to ensure that data objects from the same cluster are identical to each other. Clustering algorithms in one of the areas in data mining and it can be classified into partition, hierarchical, density based, and grid-based. Therefore, in this paper, we do a survey and review for four major hierarchical clustering algorithms called CURE, ROCK, CHAMELEON, and BIRCH. The obtained state of the art of these algorithms will help in eliminating the current problems, as well as deriving more robust and scalable algorithms for clustering.

Keywords: clustering, unsupervised learning, algorithms, hierarchical

Procedia PDF Downloads 846

Authors: Mackenzie Leake, Liyu Xia, Kamil Rocki, Wayne Imaino

Abstract:

In the Hierarchical Temporal Memory (HTM) paradigm the effect of overlap between inputs on the activation of columns in the spatial pooler is studied. Numerical results suggest that similar inputs are represented by similar sets of columns and dissimilar inputs are represented by dissimilar sets of columns. It is shown that the spatial pooler produces these results under certain conditions for the connectivity and proximal thresholds. Following the discussion of the initialization of parameters for the thresholds, corresponding qualitative arguments about the learning dynamics of the spatial pooler are discussed.

Keywords: hierarchical temporal memory, HTM, learning algorithms, machine learning, spatial pooler

Procedia PDF Downloads 312

Authors: Lokes Parvatha Kumaran S., Sakthi Jay Mahenthar C., Sathyaprakash P., Jayakumar V., Shobanadevi A.

Abstract:

With the evolution of technology, the need to solve complex computational problems like machine learning and deep learning has shot up. But even the most powerful classical supercomputers find it difficult to execute these tasks. With the recent development of quantum computing, researchers and tech-giants strive for new quantum circuits for machine learning tasks, as present works on Quantum Machine Learning (QML) ensure less memory consumption and reduced model parameters. But it is strenuous to simulate classical deep learning models on existing quantum computing platforms due to the inflexibility of deep quantum circuits. As a consequence, it is essential to design viable quantum algorithms for QML for noisy intermediate-scale quantum (NISQ) devices. The proposed work aims to explore Variational Quantum Circuits (VQC) for Deep Reinforcement Learning by remodeling the experience replay and target network into a representation of VQC. In addition, to reduce the number of model parameters, quantum information encoding schemes are used to achieve better results than the classical neural networks. VQCs are employed to approximate the deep Q-value function for decision-making and policy-selection reinforcement learning with experience replay and the target network.

Keywords: quantum computing, quantum machine learning, variational quantum circuit, deep reinforcement learning, quantum information encoding scheme

Procedia PDF Downloads 90

Authors: Yitao Lei, Xingxiang Zhai, Burra Venkata Durga Kumar

Abstract:

As the quantity and complexity of computing in large-scale software systems increase, distributed system computing becomes increasingly important. The distributed system realizes high-performance computing by collaboration between different computing resources. If there are no efficient resource scheduling resources, the abuse of distributed computing may cause resource waste and high costs. However, resource scheduling is usually an NP-hard problem, so we cannot find a general solution. However, some optimization algorithms exist like genetic algorithm, ant colony optimization, etc. The large scale of distributed systems makes this traditional optimization algorithm challenging to work with. Heuristic and machine learning algorithms are usually applied in this situation to ease the computing load. As a result, we do a review of traditional resource scheduling optimization algorithms and try to introduce a deep reinforcement learning method that utilizes the perceptual ability of neural networks and the decision-making ability of reinforcement learning. Using the machine learning method, we try to find important factors that influence the performance of distributed system computing and help the distributed system do an efficient computing resource scheduling. This paper surveys the application of deep reinforcement learning on distributed system computing resource scheduling proposes a deep reinforcement learning method that uses a recurrent neural network to optimize the resource scheduling, and proposes the challenges and improvement directions for DRL-based resource scheduling algorithms.

Keywords: resource scheduling, deep reinforcement learning, distributed system, artificial intelligence

Procedia PDF Downloads 80

Authors: Khadija Bouzaachane, El Mahdi El Guarmah

Abstract:

The classification of low-resolution satellite images has been a worthwhile and fertile field that attracts plenty of researchers due to its importance in monitoring geographical areas. It could be used for several purposes such as disaster management, military surveillance, agricultural monitoring. The main objective of this work is to classify efficiently and accurately low-resolution satellite images by using novel technics of deep learning and reinforcement learning. The images include roads, residential areas, industrial areas, rivers, sea lakes, and vegetation. To achieve that goal, we carried out experiments on the sentinel-2 images considering both high accuracy and efficiency classification. Our proposed model achieved a 91% accuracy on the testing dataset besides a good classification for land cover. Focus on the parameter precision; we have obtained 93% for the river, 92% for residential, 97% for residential, 96% for the forest, 87% for annual crop, 84% for herbaceous vegetation, 85% for pasture, 78% highway and 100% for Sea Lake.

Keywords: classification, deep learning, reinforcement learning, satellite imagery

Procedia PDF Downloads 169

Authors: Mustafa Aydın, Ali Murat Sunbul

Abstract:

Hierarchical or nested data structures usually are seen in many research areas. Especially, in the field of education, if we examine most of the studies, we can see the nested structures. Students in classes, classes in schools, schools in cities and cities in regions are similar nested structures. In a hierarchical structure, students being in the same class, sharing the same physical conditions and similar experiences and learning from the same teachers, they demonstrate similar behaviors between them rather than the students in other classes.

Keywords: hierarchical linear modeling, nested data, hierarchical structure, data structure

Procedia PDF Downloads 624

Authors: Michael Stewart

Abstract:

Mutation testing is a type of software testing proposed in the 1970s where program statements are deliberately changed to introduce simple errors so that test cases can be validated to determine if they can detect the errors. Test cases are executed against the mutant code to determine if one fails, detects the error and ensures the program is correct. One major issue with this type of testing was it became intensive computationally to generate and test all possible mutations for complex programs. This paper used reinforcement learning and parallel processing within the context of mutation testing for the selection of mutation operators and test cases that reduced the computational cost of testing and improved test suite effectiveness. Experiments were conducted using sample programs to determine how well the reinforcement learning-based algorithm performed with one live mutation, multiple live mutations and no live mutations. The experiments, measured by mutation score, were used to update the algorithm and improved accuracy for predictions. The performance was then evaluated on multiple processor computers. With reinforcement learning, the mutation operators utilized were reduced by 50 – 100%.

Keywords: automated-testing, machine learning, mutation testing, parallel processing, reinforcement learning, software engineering, software testing

Procedia PDF Downloads 164

Authors: Lei Zhang, Tingting Xu, Jun He, Zhenyu Yan

Abstract:

Email marketing is one of the most important segments of online marketing. It has been proved to be the most effective way to acquire and retain customers. The email content is vital to customers. Different customers may have different familiarity with a product, so a successful marketing strategy must personalize email content based on individual customers’ product affinity. In this study, we build our personalized email marketing strategy with three types of emails: nurture, promotion, and conversion. Each type of email has a different influence on customers. We investigate this difference by analyzing customers’ open rates, click rates and opt-out rates. Feature importance from response models is also analyzed. The goal of the marketing strategy is to improve the click rate on conversion-type emails. To build the personalized strategy, we formulate the problem as a reinforcement learning problem and adopt a Q-learning algorithm with variations. The simulation results show that our model-based strategy outperforms the current marketer’s strategy.

Keywords: email marketing, email content, reinforcement learning, machine learning, Q-learning

Procedia PDF Downloads 163

Authors: Xiuying Wang, Changliang Li, Bo Xu

Abstract:

A fixed-length feature vector is required for many machine learning algorithms in NLP field. Word embeddings have been very successful at learning lexical information. However, they cannot capture the compositional meaning of sentences, which prevents them from a deeper understanding of language. In this paper, we introduce a novel hierarchical tree long short-term memory (HTLSTM) model that learns vector representations for sentences of arbitrary syntactic type and length. We propose to split one sentence into three hierarchies: short phrase, long phrase and full sentence level. The HTLSTM model gives our algorithm the potential to fully consider the hierarchical information and long-term dependencies of language. We design the experiments on both English and Chinese corpus to evaluate our model on sentiment analysis task. And the results show that our model outperforms several existing state of the art approaches significantly.

Keywords: deep learning, hierarchical tree long short-term memory, sentence representation, sentiment analysis

Procedia PDF Downloads 325

Authors: Vani Singhal, Jitendra Parmar, Satyendra Singh Chouhan

Abstract:

Unseen class discovery has now become an important part of a machine-learning algorithm to judge new classes. Unseen classes are the classes on which the machine learning model is not trained on. With the advancement in technology and AI replacing humans, the amount of data has increased to the next level. So while implementing a model on real-world examples, we come across unseen new classes. Our aim is to find the number of unseen classes by using a hierarchical-based active learning algorithm. The algorithm is based on hierarchical clustering as well as active sampling. The number of clusters that we will get in the end will give the number of unseen classes. The total clusters will also contain some clusters that have unseen classes. Instead of first discovering unseen classes and then finding their number, we directly calculated the number by applying the algorithm. The dataset used is for intent classification. The target data is the intent of the corresponding query. We conclude that when the machine learning model will encounter real-world data, it will automatically find the number of unseen classes. In the future, our next work would be to label these unseen classes correctly.

Keywords: active sampling, hierarchical clustering, open world learning, unseen class discovery

Procedia PDF Downloads 133

Authors: Boumaraf Malak

Abstract:

The development of intelligent transportation systems (ITS) and artificial intelligence (AI) are spurring us to pave the way for the widespread adoption of autonomous vehicles (AVs). This is open again opportunities for smart roads, smart traffic safety, and mobility comfort. A highly intelligent decision-making system is essential for autonomous driving around dense, dynamic objects. It must be able to handle complex road geometry and topology, as well as complex multiagent interactions, and closely follow higher-level commands such as routing information. Autonomous vehicles have become a very hot research topic in recent years due to their significant ability to reduce traffic accidents and personal injuries. Using new artificial intelligence-based technologies handles important functions in scene understanding, motion planning, decision making, vehicle control, social behavior, and communication for AV. This paper focuses only on deep reinforcement learning-based methods; it does not include traditional (flat) planar techniques, which have been the subject of extensive research in the past because reinforcement learning (RL) has become a powerful learning framework now capable of learning complex policies in high dimensional environments. The DRL algorithm used so far found solutions to the four main problems of autonomous driving; in our paper, we highlight the challenges and point to possible future research directions.

Keywords: deep reinforcement learning, autonomous driving, deep deterministic policy gradient, deep Q-learning

Procedia PDF Downloads 48

Authors: M. Lesage, G. Raîche, M. Riopel, F. Fortin, D. Sebkhi

Abstract:

This paper describes a Web server implementation of the hierarchical aggregate assessment process in the field of education. This process describes itself as a field of teamwork assessment where teams can have multiple levels of hierarchy and supervision. This process is applied everywhere and is part of the management, education, assessment and computer science fields. The E-Assessment website named “Cluster” records in its database the students, the course material, the teams and the hierarchical relationships between the students. For the present research, the hierarchical relationships are team member, team leader and group administrator appointments. The group administrators have the responsibility to supervise team leaders. The experimentation of the application has been performed by high school students in geology courses and Canadian army cadets for navigation patrols in teams. This research extends the work of Nance that uses a hierarchical aggregation process similar as the one implemented in the “Cluster” application.

Keywords: e-learning, e-assessment, teamwork assessment, hierarchical aggregate assessment

Procedia PDF Downloads 341

Authors: Y. Alrubyli

Abstract:

Unmanned Arial Vehicles (UAVs), and more specifically, quadcopters need to be stable during their flights. Altitude stability is usually achieved by using a PID controller that is built into the flight controller software. Furthermore, the PID controller has gains that need to be tuned to reach optimal altitude stabilization during the quadcopter’s flight. For that, control system engineers need to tune those gains by using extensive modeling of the environment, which might change from one environment and condition to another. As quadcopters penetrate more sectors, from the military to the consumer sectors, they have been put into complex and challenging environments more than ever before. Hence, intelligent self-stabilizing quadcopters are needed to maneuver through those complex environments and situations. Here we show that by using online reinforcement learning with minimal background knowledge, the altitude stability of the quadcopter can be achieved using a model-free approach. We found that by using background knowledge instead of letting the online reinforcement learning algorithm wander for a while to tune the PID gains, altitude stabilization can be achieved faster. In addition, using this approach will accelerate development by avoiding extensive simulations before applying the PID gains to the real-world quadcopter. Our results demonstrate the possibility of using the trial and error approach of reinforcement learning combined with background knowledge to achieve faster quadcopter altitude stabilization in different environments and conditions.

Keywords: reinforcement learning, Q-leanring, online learning, PID tuning, unmanned aerial vehicle, quadcopter

Procedia PDF Downloads 138

Authors: Tesfaye Mengistu

Abstract:

This thesis aims to investigate the effectiveness of Reinforcement Learning (RL) for Autonomous Energy Management solutions. The study explores the potential of Model Free RL approaches, such as Monte Carlo RL and Q-learning, to improve energy management by autonomously adjusting energy management strategies to maximize efficiency. The research investigates the implementation of RL algorithms for optimizing energy consumption in a single-agent environment. The focus is on developing a framework for the implementation of RL algorithms, highlighting the importance of RL for enabling autonomous systems to adapt quickly to changing conditions and make decisions based on previous experiences. Moreover, the paper proposes RL as a novel energy management solution to address nations' CO2 emission goals. Reinforcement learning algorithms are well-suited to solving problems with sequential decision-making patterns and can provide accurate and immediate outputs to ease the planning and decision-making process. This research provides insights into the challenges and opportunities of using RL for energy management solutions and recommends further studies to explore its full potential. In conclusion, this study provides valuable insights into how RL can be used to improve the efficiency of energy management systems and supports the use of RL as a promising approach for developing autonomous energy management solutions in residential buildings.

Keywords: artificial intelligence, reinforcement learning, monte carlo, energy management, CO2 emission

Procedia PDF Downloads 51

Authors: Yihao Kuang, Bowen Ding

Abstract:

With the increasing scale and complexity of knowledge graph, modern knowledge graph contains more and more types of entity, relationship, and attribute information. Therefore, in recent years, it has been a trend for knowledge graph inference to use reinforcement learning to deal with large-scale, incomplete, and noisy knowledge graph and improve the inference effect and interpretability. The Proximal Policy Optimization (PPO) algorithm utilizes a near-end strategy optimization approach. This allows for more extensive updates of policy parameters while constraining the update extent to maintain training stability. This characteristic enables PPOs to converge to improve strategies more rapidly, often demonstrating enhanced performance early in the training process. Furthermore, PPO has the advantage of offline learning, effectively utilizing historical experience data for training and enhancing sample utilization. This means that even with limited resources, PPOs can efficiently train for reinforcement learning tasks. Based on these characteristics, this paper aims to obtain better and more efficient inference effect by introducing PPO into knowledge inference technology.

Keywords: reinforcement learning, PPO, knowledge inference, supervised learning

Procedia PDF Downloads 32

Authors: Md. Minhazul Islam, Shah Ashisul Abed Nipun, Majharul Islam, Md. Abdur Rakib Rahat, Jonayet Miah, Salsavil Kayyum, Anwar Shadaab, Faiz Al Faisal

Abstract:

The target of this research is to predict Myocardial Infarction using unsupervised Machine Learning algorithms. Myocardial Infarction Prediction related to heart disease is a challenging factor faced by doctors & hospitals. In this prediction, accuracy of the heart disease plays a vital role. From this concern, the authors have analyzed on a myocardial dataset to predict myocardial infarction using some popular Machine Learning algorithms K-Means and Hierarchical Clustering. This research includes a collection of data and the classification of data using Machine Learning Algorithms. The authors collected 345 instances along with 26 attributes from different hospitals in Bangladesh. This data have been collected from patients suffering from myocardial infarction along with other symptoms. This model would be able to find and mine hidden facts from historical Myocardial Infarction cases. The aim of this study is to analyze the accuracy level to predict Myocardial Infarction by using Machine Learning techniques.

Keywords: Machine Learning, K-means, Hierarchical Clustering, Myocardial Infarction, Heart Disease

Procedia PDF Downloads 171

Authors: Nihal Murali, Kunal Gupta, Surekha Bhanot

Abstract:

Training of artificial neural networks (ANNs) using reinforcement learning (RL) techniques is being widely discussed in the robot learning literature. The high model complexity of ANNs along with the model-free nature of RL algorithms provides a desirable combination for many robotics applications. There is a huge need for algorithms that generalize using raw sensory inputs, such as vision, without any hand-engineered features or domain heuristics. In this paper, the standard control problem of line following robot was used as a test-bed, and an ANN controller for the robot was trained on images from a live video feed using Q-learning. A virtual agent was first trained in simulation environment and then deployed onto a robot’s hardware. The robot successfully learns to traverse a wide range of curves and displays excellent generalization ability. Qualitative analysis of the evolution of policies, performance and weights of the network provide insights into the nature and convergence of the learning algorithm.

Keywords: artificial neural networks, q-learning, reinforcement learning, robot learning

Procedia PDF Downloads 346

Authors: Soofiyan Atar, Adil Shaikh, Sahil Rajpurkar, Pragnesh Bhalala, Aniket Desai, Irfan Siddavatam

Abstract:

Deep reinforcement learning (deep RL) algorithms leverage the symbolic power of complex controllers by automating it by mapping sensory inputs to low-level actions. Deep RL eliminates the complex robot dynamics with minimal engineering. Deep RL provides high-risk involvement by directly implementing it in real-world scenarios and also high sensitivity towards hyperparameters. Tuning of hyperparameters on a pneumatic quadruped robot becomes very expensive through trial-and-error learning. This paper presents an automated learning control for a pneumatic quadruped robot using sample efficient deep Q learning, enabling minimal tuning and very few trials to learn the neural network. Long training hours may degrade the pneumatic cylinder due to jerk actions originated through stochastic weights. We applied this method to the pneumatic quadruped robot, which resulted in a hopping gait. In our process, we eliminated the use of a simulator and acquired a stable gait. This approach evolves so that the resultant gait matures more sturdy towards any stochastic changes in the environment. We further show that our algorithm performed very well as compared to programmed gait using robot dynamics.

Keywords: model-based reinforcement learning, gait stability, supervised learning, pneumatic quadruped

Procedia PDF Downloads 281

Authors: Romisaa Ali

Abstract:

The Policy Gradient approach is one of the deep reinforcement learning families that combines deep neural networks (DNN) with reinforcement learning RL to discover the optimum of the control problem through experience gained from the interaction between the robot and its surroundings. In contrast to earlier policy gradient algorithms, which were unable to handle these two types of error because of over-or under-estimation introduced by the deep neural network model, this article will discuss the state-of-the-art SOTA policy gradient technique, trust region policy optimization (TRPO), by applying this method in various environments compared to another policy gradient method, the Proximal Policy Optimization (PPO), to explain their robust optimization, using this SOTA to gather experience data during various training phases after observing the impact of hyper-parameters on neural network performance.

Keywords: deep neural networks, deep reinforcement learning, proximal policy optimization, state-of-the-art, trust region policy optimization

Procedia PDF Downloads 135

Authors: Jungbhin You, Taekyun Kim, Jongho Park, Sungnam Hong, Sun-Kyu Park

Abstract:

Reinforced concrete has been mainly used in construction field because of excellent durability. However, it may lead to reduction of durability and safety due to corrosion of reinforcement steels according to damage of concrete surface. Recently, research of textile is ongoing to complement weakness of reinforced concrete. In previous research, only experiment of longitudinal length were performed. Therefore, in order to investigate the adhesion performance according to the lattice shape and the embedded length, the pull-out test was performed on the roving with parameter of the number of lateral reinforcement, the lateral reinforcement length and the lateral reinforcement spacing. As a result, the number of lateral reinforcement and the lateral reinforcement length did not significantly affect the load variation depending on the adhesion performance, and only the load analysis results according to the reinforcement spacing are affected.

Keywords: adhesion performance, lateral reinforcement, pull-out test, textile

Procedia PDF Downloads 329

Authors: Sirapop Nuannimnoi, Hojjat Baghban, Ching-Yao Huang

Abstract:

Over the past decade, with the fast development of blockchain technology since the birth of Bitcoin, there has been a massive increase in the usage of Cryptocurrencies. Cryptocurrencies are not seen as an investment opportunity due to the market’s erratic behavior and high price volatility. With the recent success of deep reinforcement learning (DRL), portfolio management can be modeled and automated. In this paper, we propose a novel DRL-based multi-agent system to automatically make proper trading decisions on multiple cryptocurrencies and gain profits in the highly volatile cryptocurrency market. We also extend this multi-agent system with horizontal federated transfer learning for better adapting to the inclusion of new cryptocurrencies in our portfolio; therefore, we can, through the concept of diversification, maximize our profits and minimize the trading risks. Experimental results through multiple simulation scenarios reveal that this proposed algorithmic trading system can offer three promising key advantages over other systems, including maximized profits, minimized risks, and adaptability.

Keywords: cryptocurrency portfolio management, algorithmic trading, federated learning, multi-agent reinforcement learning

Procedia PDF Downloads 82

Authors: Yihao Kuang, Bowen Ding

Abstract:

With the increasing scale and complexity of knowledge graph, modern knowledge graph contains more and more types of entity, relationship, and attribute information. Therefore, in recent years, it has been a trend for knowledge graph inference to use reinforcement learning to deal with large-scale, incomplete, and noisy knowledge graphs and improve the inference effect and interpretability. The Proximal Policy Optimization (PPO) algorithm utilizes a near-end strategy optimization approach. This allows for more extensive updates of policy parameters while constraining the update extent to maintain training stability. This characteristic enables PPOs to converge to improved strategies more rapidly, often demonstrating enhanced performance early in the training process. Furthermore, PPO has the advantage of offline learning, effectively utilizing historical experience data for training and enhancing sample utilization. This means that even with limited resources, PPOs can efficiently train for reinforcement learning tasks. Based on these characteristics, this paper aims to obtain a better and more efficient inference effect by introducing PPO into knowledge inference technology.

Keywords: reinforcement learning, PPO, knowledge inference

Procedia PDF Downloads 194

Authors: Ali Nadi, Ali Edrissi

Abstract:

Relief demand and transportation links availability is the essential information that is needed for every natural disaster operation. This information is not in hand once a disaster strikes. Relief demand and network condition has been evaluated based on prediction method in related works. Nevertheless, prediction seems to be over or under estimated due to uncertainties and may lead to a failure operation. Therefore, in this paper a stochastic programming model is proposed to evaluate real-time relief demand and network condition at the onset of a natural disaster. To address the time sensitivity of the emergency response, the proposed model uses reinforcement learning for optimization of the total relief assessment time. The proposed model is tested on a real size network problem. The simulation results indicate that the proposed model performs well in the case of collecting real-time information.

Keywords: disaster management, real-time demand, reinforcement learning, relief demand

Procedia PDF Downloads 271