Computer Sciences Commons^™

Learning To Assign: Towards Fair Task Assignment In Large-Scale Ride Hailing, Dingyuan Shi, Yongxin Tong, Zimu Zhou, Bingchen Song, Weifeng Lv, Qiang Yang

Research Collection School Of Computing and Information Systems

Ride hailing is a widespread shared mobility application where the central issue is to assign taxi requests to drivers with various objectives. Despite extensive research on task assignment in ride hailing, the fairness of earnings among drivers is largely neglected. Pioneer studies on fair task assignment in ride hailing are ineffective and inefficient due to their myopic optimization perspective and timeconsuming assignment techniques. In this work, we propose LAF, an effective and efficient task assignment scheme that optimizes both utility and fairness. We adopt reinforcement learning to make assignments in a holistic manner and propose a set of acceleration techniques …

Intraday Stock Trading Using Reinforcement Learning: An Investigation Of Visual Representations Of Price, Kanak Tenguria

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

In this study, we are developing a reinforcement learning-based strategy for the intraday trading of stocks. This study’s primary goals include developing an environment that can be used as a simulator for the day trading stock market and, train an agent to trade in this environment by performing actions and finding the optimal policy to maximize its reward.

This study also focuses on experimentation with different state representations to understand how data representation affects the learning system. We have experimented with three different state representations. All the representations focus on presenting the intraday stock data as images. We have chosen …

Step-Wise Deep Learning Models For Solving Routing Problems, Liang Xin, Wen Song, Zhiguang Cao, Jie Zhang

Research Collection School Of Computing and Information Systems

Routing problems are very important in intelligent transportation systems. Recently, a number of deep learning-based methods are proposed to automatically learn construction heuristics for solving routing problems. However, these methods do not completely follow Bellman's Principle of Optimality since the visited nodes during construction are still included in the following subtasks, resulting in suboptimal policies. In this article, we propose a novel step-wise scheme which explicitly removes the visited nodes in each node selection step. We apply this scheme to two representative deep models for routing problems, pointer network and transformer attention model (TAM), and significantly improve the performance of …

A Reinforcement Learning Approach To Vehicle Path Optimization In Urban Environments, Shamsa Abdulla Al Hassani

Theses

Road traffic management in metropolitan cities and urban areas, in general, is an important component of Intelligent Transportation Systems (ITS). With the increasing number of world population and vehicles, a dramatic increase in road traffic is expected to put pressure on the transportation infrastructure. Therefore, there is a pressing need to devise new ways to optimize the traffic flow in order to accommodate the growing needs of transportation systems. This work proposes to use an Artificial Intelligent (AI) method based on reinforcement learning techniques for computing near-optimal vehicle itineraries applied to Vehicular Ad-hoc Networks (VANETs). These itineraries are optimized based …

Approximate Difference Rewards For Scalable Multigent Reinforcement Learning, Arambam James Singh, Akshat Kumar

Research Collection School Of Computing and Information Systems

We address the problem of multiagent credit assignment in a large scale multiagent system. Difference rewards (DRs) are an effective tool to tackle this problem, but their exact computation is known to be challenging even for small number of agents. We propose a scalable method to compute difference rewards based on aggregate information in a multiagent system with large number of agents by exploiting the symmetry present in several practical applications. Empirical evaluation on two multiagent domains—air-traffic control and cooperative navigation, shows better solution quality than previous approaches.

Learning Index Policies For Restless Bandits With Application To Maternal Healthcare, Arpita Biswas, Gaurav Aggarwal, Pradeep Varakantham, Milind Tambe

Research Collection School Of Computing and Information Systems

In many community health settings, it is crucial to have a systematic monitoring and intervention process to ensure that the patients adhere to healthcare programs, such as periodic health checks or taking medications. When these interventions are expensive, they can be provided to only a fixed small fraction of the patients at any period of time. Hence, it is important to carefully choose the beneficiaries who should be provided with interventions and when. We model this scenario as a restless multi-armed bandit (RMAB) problem, where each beneficiary is assumed to transition from one state to another depending on the intervention …

Approximate Difference Rewards For Scalable Multigent Reinforcement Learning, Arambam James Singh, Akshat Kumar, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

We address the problem ofmultiagent credit assignment in a large scale multiagent system. Difference rewards (DRs) are an effective tool to tackle this problem, but their exact computation is known to be challenging even for small number of agents. We propose a scalable method to compute difference rewards based on aggregate information in a multiagent system with large number of agents by exploiting the symmetry present in several practical applications. Empirical evaluation on two multiagent domains - air-traffic control and cooperative navigation, shows better solution quality than previous approaches.

A Deep Reinforcement Learning-Based Dynamic Computational Offloading Method For Cloud Robotics, Manoj Penmetcha, Byung-Cheol Min

Purdue University Libraries Open Access Publishing Fund

Robots come with a variety of computing capabilities, and running computationally-intense applications on robots is sometimes challenging on account of limited onboard computing, storage, and power capabilities. Meanwhile, cloud computing provides on-demand computing capabilities, and thus combining robots with cloud computing can overcome the resource constraints robots face. The key to effectively offloading tasks is an application solution that does not underutilize the robot's own computational capabilities and makes decisions based on crucial cost parameters such as latency and CPU availability. In this paper, we formulate the application offloading problem as a Markovian decision process and propose a deep reinforcement …

Learning How To Search: Generating Effective Test Cases Through Adaptive Fitness Function Selection, Hussein Khalid Almulla

Theses and Dissertations

Search-based test generation is guided by feedback from one or more fitness functions— scoring functions that judge solution optimality. Choosing informative fitness functions is crucial to meeting the goals of a tester. Unfortunately, many goals—such as forcing the class-under-test to throw exceptions, increasing test suite diversity, and attaining Strong Mutation Coverage—do not have effective fitness function formulations. We propose that meeting such goals requires treating fitness function identification as a secondary optimization step. An adaptive algorithm that can vary the selection of fitness functions could adjust its selection throughout the generation process to maximize goal attainment, based on the current …

Playing Pong Using Q-Learning, Akash Kumar

West Chester University Master’s Theses

This thesis involves the use of a reinforcement learning algorithm (RL) called Q-learning to train a Q-agent to play a game of Pong against a near-perfect opponent. Compared to previously related work which trained Pong RL agents by combining Q-learning with deep learning in an algorithm known as Deep Q-Networks, the work presented in this paper takes advantage of known environment constraints of the custom-made Pong environment to train the agent using one-step Q-learning alone. In addition, the thesis explores ways of making the Q-learning more efficient by converting Markov Decision Processes (MDPs) to Partially Observable Markov Decision Processes (POMDPs), …

Multi-Actor-Attention-Critic Reinforcement Learning For Central Place Foraging Swarms, Ning Yang, Qi Lu, Kele Xu, Bo Ding, Zijian Gao

Computer Science Faculty Publications

Multiple agents with relatively low cost, decentralized control, and robustness have the advantages of completing a foraging task more efficiently than a single advanced robot. Despite many foraging algorithms are efficient in multiple robot systems, most are pre-designed or not very adaptive to different environments since they have to evolve the parameters of the foraging algorithm in each different environment. Besides, designing an efficient collision avoidance strategy for multiple agents is a challenge. Addressing these issues, we introduce the multi-actor-attention-critic(MAAC) reinforcement learning method into the multiple foraging agents. We train the foraging strategy for multiple simulated agents. We compare our …

Multiagent Q-Learning Based Uav Trajectory Planning For Effective Situationalawareness, Erdal Akin, Kubi̇lay Demi̇r, Hali̇l Yetgi̇n

Turkish Journal of Electrical Engineering and Computer Sciences

In the event of a natural disaster, arrival time of the search and rescue (SAR) teams to the affected areas is of vital importance to save the life of the victims. In particular, when an earthquake occurs in a geographically large area, reconnaissance of the debris within a short-time is critical for conducting successful SAR missions. An effective and quick situational awareness in postdisaster scenarios can be provided via the help of unmanned aerial vehicles (UAVs). However, off-the-shelf UAVs suffer from the limited communication range as well as the limited airborne duration due to battery constraints. If telecommunication infrastructure is …

Increasing Software Reliability Using Mutation Testing And Machine Learning, Michael Allen Stewart

CCAC Theses and Dissertations

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. The goal of mutation testing was to reduce complex program errors by preventing the related simple 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 …

Markov Decision Processes With Embedded Agents, Luke Harold Miles

Theses and Dissertations--Computer Science

We present Markov Decision Processes with Embedded Agents (MDPEAs), an extension of multi-agent POMDPs that allow for the modeling of environments that can change the actuators, sensors, and learning function of the agent, e.g., a household robot which could gain and lose hardware from its frame, or a sovereign software agent which could encounter viruses on computers that modify its code. We show several toy problems for which standard reinforcement-learning methods fail to converge, and give an algorithm, `just-copy-it`, which learns some of them. Unlike MDPs, MDPEAs are closed systems and hence their evolution over time can be treated as …

Q-Learning Based Routing Protocol For Congestion Avoidance, Daniel Godfrey, Beom Su Kim, Haoran Miao, Babar Shah, Bashir Hayat, Imran Khan, Tae Eung Sung, Ki Il Kim

All Works

The end-to-end delay in a wired network is strongly dependent on congestion on intermediate nodes. Among lots of feasible approaches to avoid congestion efficiently, congestion-aware routing protocols tend to search for an uncongested path toward the destination through rule-based approaches in reactive/incident-driven and distributed methods. However, these previous approaches have a problem accommodating the changing network environments in autonomous and self-adaptive operations dynamically. To overcome this drawback, we present a new congestion-aware routing protocol based on a Q-learning algorithm in software-defined networks where logically centralized network operation enables intelligent control and management of network resources. In a proposed routing protocol, …

Relational-Grid-World: A Novel Relational Reasoning Environment And An Agentmodel For Relational Information Extraction, Faruk Küçüksubaşi, Eli̇f Sürer

Turkish Journal of Electrical Engineering and Computer Sciences

Reinforcement learning (RL) agents are often designed specifically for a particular problem and they generallyhave uninterpretable working processes. Statistical methods-based agent algorithms can be improved in terms ofgeneralizability and interpretability using symbolic artificial intelligence (AI) tools such as logic programming. Inthis study, we present a model-free RL architecture that is supported with explicit relational representations of theenvironmental objects. For the first time, we use the PrediNet network architecture in a dynamic decision-making problemrather than image-based tasks, and multi-head dot-product attention network (MHDPA) as a baseline for performancecomparisons. We tested two networks in two environments -i.e., the baseline box-world environment and …

Deep Q-Network-Based Noise Suppression For Robust Speech Recognition, Tae-Jun Park, Joon-Hyuk Chang

Turkish Journal of Electrical Engineering and Computer Sciences

This study develops the deep Q-network (DQN)-based noise suppression for robust speech recognition purposes under ambient noise. We thus design a reinforcement algorithm that combines DQN training with a deep neural networks (DNN) to let reinforcement learning (RL) work for complex and high dimensional environments like speech recognition. For this, we elaborate on the DQN training to choose the best action that is the quantized noise suppression gain by the observation of noisy speech signal with the rewards of DQN including both the word error rate (WER) and objective speech quality measure. Experiments demonstrate that the proposed algorithm improves speech …

Reinforcement Learning Environment For Orbital Station-Keeping, Armando Herrera Iii

Theses and Dissertations

In this thesis, a Reinforcement Learning Environment for orbital station-keeping is created and tested against one of the most used Reinforcement Learning algorithm called Proximal Policy Optimization (PPO). This thesis also explores the foundations of Reinforcement Learning, from the taxonomy to a description of PPO, and shows a thorough explanation of the physics required to make the RL environment. Optuna optimizes PPO's hyper-parameters for the created environment via distributed computing. This thesis then shows and analysis the results from training a PPO agent six times.

Deep Q Learning Applied To Stock Trading, Agnibh Dasgupta

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Developing a strategy for stock trading is a vital task for investors. However, it is challenging to obtain an optimal strategy, given the complex and dynamic nature of the stock market. This thesis aims to explore the applications of Reinforcement Learning with the goal of maximizing returns from market investment, keeping in mind the human aspect of trading by utilizing stock prices represented as candlestick graphs. Furthermore, the algorithm studies public interest patterns in form of graphs extracted from Google Trends to make predictions. Deep Q learning has been used to train an agent based on fused images of stock …

Micro Grid Control Optimization With Load And Solar Prediction, Shaju Saha

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Using renewable energy can save money and keep the environment cleaner. Installing a solar PV system is a one-time cost but it can generate energy for a lifetime. Solar PV does not generate carbon emissions while producing power. This thesis evaluates the value of being able to make accurate predictions in the use of solar energy. It uses predicted solar power and load for a system and a battery to store the energy for future use and calculates the operating cost or profit in several designed conditions. Various factors like a different place, tuning the capacity of sources, changing buy/sell …

Reinforcement Learning For Zone Based Multiagent Pathfinding Under Uncertainty, Jiajing Ling, Tarun Gupta, Akshat Kumar

Research Collection School Of Computing and Information Systems

We address the problem of multiple agents finding their paths from respective sources to destination nodes in a graph (also called MAPF). Most existing approaches assume that all agents move at fixed speed, and that a single node accommodates only a single agent. Motivated by the emerging applications of autonomous vehicles such as drone traffic management, we present zone-based path finding (or ZBPF) where agents move among zones, and agents' movements require uncertain travel time. Furthermore, each zone can accommodate multiple agents (as per its capacity). We also develop a simulator for ZBPF which provides a clean interface from the …

Deep Reinforcement Learning Approach To Solve Dynamic Vehicle Routing Problem With Stochastic Customers, Waldy Joe, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

In real-world urban logistics operations, changes to the routes and tasks occur in response to dynamic events. To ensure customers’ demands are met, planners need to make these changes quickly (sometimes instantaneously). This paper proposes the formulation of a dynamic vehicle routing problem with time windows and both known and stochastic customers as a route-based Markov Decision Process. We propose a solution approach that combines Deep Reinforcement Learning (specifically neural networks-based TemporalDifference learning with experience replay) to approximate the value function and a routing heuristic based on Simulated Annealing, called DRLSA. Our approach enables optimized re-routing decision to be generated …

Learning To Collaborate In Multi-Module Recommendation Via Multi-Agent Reinforcement Learning Without Communication, Xu He, An Bo, Yanghua Li, Haikai Chen, Rundong Wang, Xinrun Wang, Runsheng Yu, Xin Li, Zhirong Wang

Research Collection School Of Computing and Information Systems

With the rise of online e-commerce platforms, more and more customers prefer to shop online. To sell more products, online platforms introduce various modules to recommend items with different properties such as huge discounts. A web page often consists of different independent modules. The ranking policies of these modules are decided by different teams and optimized individually without cooperation, which might result in competition between modules. Thus, the global policy of the whole page could be sub-optimal. In this paper, we propose a novel multi-agent cooperative reinforcement learning approach with the restriction that different modules cannot communicate. Our contributions are …

Allosteric Regulation At The Crossroads Of New Technologies: Multiscale Modeling, Networks, And Machine Learning, Gennady M. Verkhivker, Steve Agajanian, Guang Hu, Peng Tao

Mathematics, Physics, and Computer Science Faculty Articles and Research

Allosteric regulation is a common mechanism employed by complex biomolecular systems for regulation of activity and adaptability in the cellular environment, serving as an effective molecular tool for cellular communication. As an intrinsic but elusive property, allostery is a ubiquitous phenomenon where binding or disturbing of a distal site in a protein can functionally control its activity and is considered as the “second secret of life.” The fundamental biological importance and complexity of these processes require a multi-faceted platform of synergistically integrated approaches for prediction and characterization of allosteric functional states, atomistic reconstruction of allosteric regulatory mechanisms and discovery of …

Joint Optimization Control Of Energy Storage System Management And Demand Response, Xueying Gao, Tang Hao, Gangzhong Miao, Zhaowu Ping

Journal of System Simulation

Abstract: The joint optimization problem of energy management and demand response were studied in order to reduce the long-run cost of electricity users equipped with energy storage unit and smart applications, and to increase their benefits meanwhile. The goals were achieved by controlling both the energy storage unit (charging, discharging, or idle) and the load service (access or delay). Based on the random nature of solar photovoltaic, load demand electricity and electricity price, the joint optimization problem was modeled as infinite-horizon Markov decision process model, and Q-learning algorithm was proposed to find the optimal solution. Simulation results show that the …

Analysis And Optimization Of The Action Chain Mechanism In Agent2d Underlying In Robocup2d Soccer League, Chen Bing, Feifan Xu, Hanyan Xu, Zekai Cheng, Liu Cheng

Journal of System Simulation

Abstract: In the RoboCup2D soccer league, Agent2D is one of the most widely used underlying team in China. Data transmission noise and the incomplete action chain mechanism make the underlying teams using Agent2D be lack of flexibility. This paper introduces an action correcting parameter and optimizes the operation of the action chain by reinforcement learning mechanism. The performance of the Agent2D underlying team is improved in the game and the adaptability of the team is enhanced. Simulation experiment results show that this method has a certain effect.

Monte Carlo Tree Search Applied To A Modified Pursuit/Evasion Scotland Yard Game With Rendezvous Spaceflight Operation Applications, Joshua A. Daughtery

Theses and Dissertations

This thesis takes the Scotland Yard board game and modifies its rules to mimic important aspects of space in order to facilitate the creation of artificial intelligence for space asset pursuit/evasion scenarios. Space has become a physical warfighting domain. To combat threats, an understanding of the tactics, techniques, and procedures must be captured and studied. Games and simulations are effective tools to capture data lacking historical context. Artificial intelligence and machine learning models can use simulations to develop proper defensive and offensive tactics, techniques, and procedures capable of protecting systems against potential threats. Monte Carlo Tree Search is a bandit-based …

Using Taint Analysis And Reinforcement Learning (Tarl) To Repair Autonomous Robot Software, Damian Lyons, Saba Zahra

Faculty Publications

It is important to be able to establish formal performance bounds for autonomous systems. However, formal verification techniques require a model of the environment in which the system operates; a challenge for autonomous systems, especially those expected to operate over longer timescales. This paper describes work in progress to automate the monitor and repair of ROS-based autonomous robot software written for an a-priori partially known and possibly incorrect environment model. A taint analysis method is used to automatically extract the data-flow sequence from input topic to publish topic, and instrument that code. A unique reinforcement learning approximation of MDP utility …

Applying Imitation And Reinforcement Learning To Sparse Reward Environments, Haven Brown

Computer Science and Computer Engineering Undergraduate Honors Theses

The focus of this project was to shorten the time it takes to train reinforcement learning agents to perform better than humans in a sparse reward environment. Finding a general purpose solution to this problem is essential to creating agents in the future capable of managing large systems or performing a series of tasks before receiving feedback. The goal of this project was to create a transition function between an imitation learning algorithm (also referred to as a behavioral cloning algorithm) and a reinforcement learning algorithm. The goal of this approach was to allow an agent to first learn to …

Intrinsic Curiosity In Reinforcement Learning By Improving Next State Prediction, Paul Lewis Lobo

Computer Science and Engineering Theses - Archive

In Reinforcement Learning, an agent receives feedback from the environment in the form of an extrinsic reward. It learns to take actions that maximize this extrinsic reward. However, to start learning, the agent needs to be able to get feedback from the environment by using random actions. This works in environments with frequent rewards, however, in environments where the rewards are sparse the probability of reaching any reward even once becomes very low. One way to explore an environment efficiently is for the agent to generate its own intrinsic reward by using the prediction error from a model that is …