Reinforcement Learning for Resource Constrained Project Scheduling Problem with Activity Iterations and Crashing

As vehicular technology advances, intelligent vehicles generate numerous computation‐intensive tasks, challenging the computational resources of both the vehicles and the Internet of Vehicles (IoV). Traditional IoV struggles with fixed network structures and limited scalability, unable to meet the growing computational demands and next‐generation mobile communication technologies. In congested areas, near‐end Mobile Edge Computing (MEC) resources are often overtaxed, while far‐end MEC servers are underused, resulting in poor service quality. A novel network framework utilizing sixth‐generation mobile communication (6G) and digital twin technologies, combined with task migration, promises to alleviate these inefficiencies. To address these challenges, a task migration and re‐offloading model based on task attribute classification is introduced, employing a hybrid deep reinforcement learning (DRL) algorithm—Dueling Double Q Network DDPG (QDPG). This algorithm merges the strengths of the Deep Deterministic Policy Gradient (DDPG) and the Dueling Double Deep Q‐Network (D3QN), effectively handling continuous and discrete action domains to optimize task migration and re‐offloading in IoV. The inclusion of the Mini Batch K‐Means algorithm enhances learning efficiency and optimization in the DRL algorithm. Experimental results show that QDPG significantly boosts task efficiency and computational performance, providing a robust solution for resource allocation in IoV.

Using Deep Reinforcement Learning (DRL) algorithm to deal with autonomous driving tasks usually have unsatisfied performance due to lack of robustness and means to escape local optimum. In this article, we designs a Survival-Oriented Reinforcement Learning (SORL) model that tackle these problems by setting survival rather than maximize total reward as first priority. In SORL model, we model autonomous driving task as Constrained Markov Decision Process (CMDP) and introduce Negative-Avoidance Function to learn from previous failure. The SORL model greatly speed up the training process and improve the robustness of normal Deep Reinforcement Learning algorithm.

<span>The utilization of games in training the reinforcement learning (RL) agent is to describe the complex and high-dimensional real-world data. By utilizing games, RL researchers will be able to evade high experimental costs in training an agent to do intelligence tasks. The objective of this research is to generate intelligent agent behaviors in multi-agent game artificial intelligence (AI) using deep reinforcement learning (DRL) algorithm. A basic RL algorithm called deep Q network is chosen to be implemented. The agent is trained by the environment's raw pixel images and the action list information. The experiments conducted by using this algorithm show the agent’s decision-making ability in choosing a favorable action. In the default setting for the algorithm, the training is set into 1 epoch and 0.0025 learning rate. The number of training iterations is set to one as the training function will be repeatedly called for every 4-timestep. However, the author also experimented with two different scenarios in training the agent and compared the results. The experimental findings demonstrate that our agents learn correctly and successfully while actively participating in the game in real time. Additionally, our agent can quickly adjust against a different enemy on a varied map because of the observed knowledge from prior training.</span>

Multi-agent reinforcement learning dealing with hybrid action spaces: A case study for off-grid oriented renewable building energy system

In this paper, motivated by the production process of electronic control modules in the digital electronic detonators industry, we study a multi-objective flexible flow shop scheduling problem. The objective is to find a feasible schedule that minimizes both the makespan and the total tardiness. Considering the constraints imposed by the jobs and the machines throughout the manufacturing process, a mixed integer programming model is formulated. By transforming the scheduling problem into a Markov decision process, the agent state features and the actions are designed based on the processing status of the machines and the jobs, along with heuristic rules. Furthermore, a reward function based on the optimization objectives is designed. Based on the deep reinforcement learning algorithm, the Dueling Double Deep Q-Network (D3QN) algorithm is designed to solve the scheduling problem by incorporating the target network, the dueling network, and the experience replay buffer. The D3QN algorithm is compared with heuristic rules, the genetic algorithm (GA), and the optimal solutions generated by Gurobi. The ablation experiments are designed. The experimental results demonstrate the high performance of the D3QN algorithm with the target network and the dueling network proposed in this paper. The scheduling model and the algorithm proposed in this paper can provide theoretical support to make the production plan of electronic control modules reasonable and improve production efficiency.

Performance of planned activities not always leads to the achievement of planned results in innovation projects with a high degree of uncertainty. Management of such specific projects requires the usage of specific methods and processes. It is necessary to develop own stochastic process methods rather than use classical methods of deterministic management. The main peculiarity of stochastic processes of projects consists in the inability to carry out more than one experiment. Implementation of a project is a stochastic process, which is carried out only once. For the purposes of the research, stochastic project management is the process of organisation, planning and control over projects, in which the decisions and actions of managers are described by stochastic functions. If the project realisation is described by stochastic processes, the project management process is indeed described by stochastic processes. This research suggests a project management approach based on the focus on the project product and project management as stochastic processes based on stochastic functions. It is demonstrated that stochastic function values, which underlie the stochastic processes, are formed by the intellectual instruments of those involved in the project and are developed on the basis of their knowledge and skills. The latter, in turn, are the result of studying and practical work on the project. Therefore, it is difficult to predict decisions and actions of managers and contractors, even if internal and external influences on them are specified. Then, any decisions or actions of such persons with regard to the external observer are described by stochastic functions. The purpose of this study is to describe the processes of stochastic project management. The purpose of the study is the project management process. The subject of research is the methods of stochastic project management. Within the framework of the study, all groups of processes of stochastic control will be mathematically described and the conditions of their impact determined. The processes of stochastic project management are outlined and formally presented. These are the processes of project management organisation, the processes of project management support, processes of project content definition, processes of defining the resources, required for the project works, processes of project planning, processes of influence on contractors of actions (works).

The energy harvesting D2D-enabled cellular network (EH-DCN) has emerged as a promising approach to address the issues of energy supply and spectrum utilization. Most of existing works mainly focus on the throughput, while the information freshness, which is critical to the time-sensitive applications, has been rarely explored. Considering above facts, we aim to develop an optimal mode selection and resource allocation (MSRA) policy that maximizes the long-term overall throughput of a time-varying dynamic EH-DCN, subject to an age of information (AoI) constraint. As the MSRA policy involves both continuous variables (i.e., bandwidth, power, and time allocations) and discrete variables (i.e., mode selection and channel allocation), the optimization problem is proved to be nonconvex and NP-hard. To solve the nonconvex NP-hard problem, we exploit a deep reinforcement learning (DRL) approach, called MSRA twin delayed deep deterministic policy gradient (MSRA-TD3). The MSRA-TD3 employs a double critic network structure to better fit the reward function, and could effectively mitigate the overestimation of Q-value in deep deterministic policy gradient (DDPG), which is a classical DRL algorithm. It is worth noting that in the design of the MSRA-TD3, we use the throughput of user equipments (UEs) at the previous time slot as a state to bypass the channel state information estimation resulting from the time-varying dynamic environment, and take the weights of throughput and AoI penalty into the reward function to evaluate two performance. Simulations demonstrate that the established MSRA-TD3 algorithm achieves better performance in terms of throughput and AoI than comparison DRL algorithms.

Problem definition: The beer game is widely used in supply chain management classes to demonstrate the bullwhip effect and the importance of supply chain coordination. The game is a decentralized, multiagent, cooperative problem that can be modeled as a serial supply chain network in which agents choose order quantities while cooperatively attempting to minimize the network’s total cost, although each agent only observes local information. Academic/practical relevance: Under some conditions, a base-stock replenishment policy is optimal. However, in a decentralized supply chain in which some agents act irrationally, there is no known optimal policy for an agent wishing to act optimally. Methodology: We propose a deep reinforcement learning (RL) algorithm to play the beer game. Our algorithm makes no assumptions about costs or other settings. As with any deep RL algorithm, training is computationally intensive, but once trained, the algorithm executes in real time. We propose a transfer-learning approach so that training performed for one agent can be adapted quickly for other agents and settings. Results: When playing with teammates who follow a base-stock policy, our algorithm obtains near-optimal order quantities. More important, it performs significantly better than a base-stock policy when other agents use a more realistic model of human ordering behavior. We observe similar results using a real-world data set. Sensitivity analysis shows that a trained model is robust to changes in the cost coefficients. Finally, applying transfer learning reduces the training time by one order of magnitude. Managerial implications: This paper shows how artificial intelligence can be applied to inventory optimization. Our approach can be extended to other supply chain optimization problems, especially those in which supply chain partners act in irrational or unpredictable ways. Our RL agent has been integrated into a new online beer game, which has been played more than 17,000 times by more than 4,000 people.

The continuously changing nature of stock markets poses a non-trivial challenge to build automated trading agents that timely assist traders in their decision makings. Fixed sets of trading rules and offline pre-trained models are inefficient to adapt regarding the real-time fluctuations on the stock markets. Deep Reinforcement Learning (DRL) algorithms train autonomous agents that could potentially address such highly dynamic environments by integrating the generalization power of artificial neural networks with the online learning through experiences gained in the interactions with the environment. We investigate the capability of three DRL algorithms, namely Deep Deterministic Policy Gradient (DDPG), Twin Delayed DDPG (TD3), and Soft Actor-Critic (SAC), for tackling the automated stock trading problem. We employ two datasets, from the US and Vietnam markets, with different characteristics and market trends, on which the DRL-trained agents are compared against a random trading agent. Experimental results indicate the potentials of these DRL algorithms and also exhibit their pitfalls when being applied in datasets where the majority of the stocks are not up-trending. We propose a simple, but effective, technique to assist the agents to minimize their losses.

The online 3D bin packing problem(3D-BPP) is widely used in the logistics industry and is of great practical significance for promoting the intelligent transformation of the industry. The heuristic algorithm relies too much on manual experience to formulate more perfect packing rules. In recent years, many scholars solve 3D-BPP via deep reinforcement learning(DRL) algorithms. However, they ignore many skills used in manual packing, one of the most important skill is workers put the item aside if the item is packed improperly. Inspired by this skill, we propose a DRL algorithm with a buffer zone. Firstly, we define the wasted space and the buffer zone. And then, we integrate them into the DRL algorithm framework. Importantly, we compare the bin utilization with di erent thresholds of wasted space and di erent buffer zone sizes. Experimental results show that our algorithm outperforms existing heuristic algorithms and DRL algorithms.

Reinforcement Learning (RL) has become one of the most powerful methods in Artificial Intelligence (AI) which allows a system to learn as it is engaged in an interaction with its environment and to maximize its actions by performing a trial and error process. Although classical RL algorithms can give us a fundamental idea on RL, like the Q-Learning, its usefulness wanes in high-dimensional or continuous-state spaces. To overcome these shortcomings, Deep Reinforcement Learning (DRL) algorithms including Deep Q-Networks (DQN) build on neural networks to learn action-value functions, allowing horizontal scalability and more efficient learning. This paper reports on the experimental comparison of Q-Learning and DQN based on the environment CartPole-v1. Both of the algorithms were trained in the controlled environment and tested under various metrics that include cumulative rewards, success rate, convergence speed, safety (failure rate), and path efficiency. Findings indicate that Q-Learning moves towards moderate stability with slower convergence but DQN takes shorter learning time, is more reliable and performs better. Such results indicate the ground-breaking potential of the DRL in the progress of AI toward transcending classical RL restrictions. Future research topics encompass implementation of more challenging experimental settings, a test of other DRL algorithms (e.g., PPO, SAC), and generalization, scalability and safety in real-world environments.

Deep Reinforcement Learning (DRL) algorithm provides an effective and powerful way for the computer learning to make decisions according to what the computer sees, the most famous application of DRL is training the computer to play computer games, such as the computer Go and Atari Games. In this paper, we present that the DRL can used to improve the classical PID controller by training an adaptive PID controller with its parameters change according to the changing state, we name our new controller as DRPID, the deep reinforcement learning algorithm that we used to train the PID controller in this paper is deep deterministic policy gradient, which is very suitable to solve continue action control problem. We test our DRPID algorithm by training it to control an inverted pendulum in the OpenAI gym simulation environment, and we found DRPID controller works very well, outperforms the common PID controller with fixed parameters, by a great margin.

The growing number of complex and heterogeneous Internet of Things (IoT) applications has imposed a high demand for scarce communications and computing resources. To meet this stringent requirement, it is desirable to develop large-scale highly adaptive online resource allocation strategies to streamline existing network operations. Deep reinforcement learning (DRL), which combines the merits of reinforcement learning and deep learning, is capable of addressing complex decision-making tasks, thus enabling efficient online resource allocation. In this article, we present a DRL-based resource allocation framework. We begin a discussion on DRL basics and review its several recent applications. Then, we develop two new DRL algorithms that facilitate unlocking the potential of DRL and offer viable solutions to many more complex resource allocation problems. The first one tackles an optimization problem exposed to mixed (discrete and continuous) action spaces and bound by a number of highly non-linear quality-of-service (QoS) constraints. The second one extends the single-agent DRL to a more challenging multi-agent DRL by introducing a novel semi-distributed architecture. Finally, we discuss the challenges and future visions of applying DRL to real-world IoT networks.

In recent years, deep reinforcement learning has combined the advantages of reinforcement learning and deep learning, and has made great progress in decision-making tasks. However, the training of deep reinforcement learning requires frequent interactions between the agent and the environment and repeated experiments. Adversaries have chances to poison the sample data collected by the agent by attacking the experimental environment in the training process, thereby bringing security risks and serious consequences to the training process of reinforcement learning. This work is committed to addressing the security risks in the field of deep reinforcement learning. However, this work improves the algorithm from the perspective of sample data filtering, and improves the security performance of deep reinforcement learning algorithm. There are two contributions in this work: one is to defend against adversarial attacks against deep reinforcement learning through cluster analysis and sample value evaluation; the other is to propose a deep reinforcement learning algorithm based on sample value evaluation on the basis of deterministic strategy gradient algorithm. The algorithm uses the clustering method to classify the sample pool, and measures the contribution value and security risk of the sample to the model training through the sample value evaluation. The classic game experiments show that the proposed algorithm is safe and effective. It reduces the threat of the agent falling into the adversarial sample attack and improves the training performance of deep reinforcement learning.

With the vigorous development of computer-related technology, the “perception + decision” paradigm of the combination of deep learning and reinforcement learning has become a research hotspot. Nowadays, deep reinforcement learning algorithms have been successfully applied to the fields of games, industry and commerce. However, deep reinforcement learning algorithms often fall into the dilemma of “exploration” and “exploitation”, and the effect of these algorithms is easily affected by the quality of hyperparameters. In order to make up for the defects mentioned above, this paper introduces the particle swarm based reinforcement learning framework (PRL). Compared with the standard reinforcement learning algorithms, this framework greatly improves the exploration ability and obtains better scores in a series of gym experimental tests.KeywordsReinforcement learningParticle swarm optimizationTwin delayed deep deterministic policy gradients