Efficient Reinforcement Learning Research Articles

Energy efficient deep reinforcement learning approach to control the traffic flow in iot networks for smart city

Energy efficient deep reinforcement learning approach to control the traffic flow in iot networks for smart city

Efficient Reinforcement Learning With Impaired Observability: Learning to Act With Delayed and Missing State Observations

Efficient Reinforcement Learning With Impaired Observability: Learning to Act With Delayed and Missing State Observations

A novel energy-efficiency framework for UAV-assisted networks using adaptive deep reinforcement learning

In the air-to-ground transmissions, the lifespan of the network is based on the “unmanned aerial vehicle's (UAV)” life span because of the limited battery capacity. Thus, the enhancement of energy efficiency and the outage of the ground candidate’s minimization are significant factors of the network functionality. UAV-aided transmission can highly enhance the spectrum efficacy and coverage. Because of their flexible deployment and the high maneuverability, the UAVs can be the best alternative for the situations where the “Internet of Things (IoT)” systems utilize more energy to attain the essential information rate, when they are far away from the terrestrial base station. Therefore, it is significant to win over the few troubles in the conventional UAV-aided efficiency approaches. Thus, this proposed work is aimed to design an innovative energy efficiency framework in the UAV-assisted network using a reinforcement learning mechanism. The energy efficiency optimization in the UAV offers better wireless coverage to the static and mobile ground user. Presently, reinforcement learning techniques effectively optimize the energy efficiency rate of the system by employing the 2D trajectory mechanism, which effectively removes the interference rate attained in the nearby UAV cells. The main objective of the recommended framework is to maximize the energy efficiency rate of the UAV network by performing the joint optimization using UAV 3D trajectory, with the energy utilized during interference accounting, and connected user counts. Hence, an efficient Adaptive Deep Reinforcement Learning with Novel Loss Function (ADRL-NLF) framework is designed to provide a better energy efficiency rate to the UAV network. Moreover, the parameter of ADRL is tuned using the Hybrid Energy Valley and Hermit Crab (HEVHC) algorithm. Various experimental observations are performed to observe the effectualness rate of the recommended energy efficiency model for UAV-based networks over the classical energy efficiency framework in UAV Networks.

Deep reinforcement learning for solving car resequencing with selectivity banks in automotive assembly shops

In the automobile manufacturing process, the complexity of the production environment and the different objectives of the upstream and downstream shops necessitate the resequencing of the car sequences using buffers. This paper addresses a car resequencing problem in automotive assembly shops by utilising selectivity banks to reshuffle the given upstream sequences to minimise the number of violations of sequencing rules in the downstream sequence. A new resequencing approach combining heuristics and deep reinforcement learning is proposed to solve the problem. Heuristics solve the automobile storage problem, while a deep reinforcement learning method based on proximal policy optimisation addresses the automobile release problem. Three state matrices, agent actions, and the reward function are designed based on the characteristics of the objective and selectivity banks. Additionally, a novel network structure combining convolutional neural networks and long short-term memory networks is proposed to train the agent. The results demonstrate that the proposed method outperforms two efficient deep reinforcement learning algorithms and two heuristics and obtains better solutions in handling dynamic events.

A Deep Reinforcement Learning Approach to Injection Speed Control in Injection Molding Machines with Servomotor-Driven Constant Pump Hydraulic System

The control of the injection speed in hydraulic injection molding machines is critical to product quality and production efficiency. This paper analyzes servomotor-driven constant pump hydraulic systems in injection molding machines to achieve optimal tracking control of the injection speed. We propose an efficient reinforcement learning (RL)-based approach to achieve fast tracking control of the injection speed within predefined time constraints. First, we construct a precise Markov decision process model that defines the state space, action space, and reward function. Then, we establish a tracking strategy using the Deep Deterministic Policy Gradient RL method, which allows the controller to learn optimal policies by interacting with the environment. Careful attention is also paid to the network architecture and the definition of states/actions to ensure the effectiveness of the proposed method. Extensive numerical results validate the proposed approach and demonstrate accurate and efficient tracking of the injection velocity. The controller’s ability to learn and adapt in real time provides a significant advantage over the traditional Proportion Integration Differentiation controller. The proposed method provides a practical solution to the challenge of maintaining accurate control of the injection speed in the manufacturing process.

Efficient deep reinforcement learning based task scheduler in multi cloud environment

Task scheduling problem (TSP) is huge challenge in cloud computing paradigm as number of tasks comes to cloud application platform vary from time to time and all the tasks consists of variable length, runtime capacities. All these tasks may generated from various heterogeneous resources which comes onto cloud console directly effects the performance of cloud paradigm with increase in makespan, energy consumption, resource costs. Traditional task scheduling algorithms cannot handle these type of complex workloads in cloud paradigm. Many authors developed Task Scheduling algorithms by using metaheuristic techniques, hybrid approaches but all these algorithms give near optimal solutions but still TSP is a highly challenging and dynamic scenario as it resembles NP hard problem. Therefore, to tackle the TSP in cloud computing paradigm and schedule the tasks in an effective way in cloud paradigm, we formulated Adaptive Task scheduler which segments all the tasks comes to cloud console as sub tasks and fed these to the scheduler which is modeled by Improved Asynchronous Advantage Actor Critic Algorithm(IA3C) to generate schedules. This scheduling process is carried out in two stages. In first stage, all incoming tasks are segmented as sub tasks. After segmentation, all these sub tasks according to their size, execution time, communication time are grouped together and fed to the (ATSIA3C) scheduler. In the second stage, it checks for the above said constraints and disperse them onto the corresponding suitable processing capacity VMs resided in datacenters. Proposed ATSIA3C is simulated on Cloudsim. Extensive simulations are conducted using both fabricated worklogs and as well as realtime supercomputing worklogs. Our proposed mechanism evaluated over baseline algorithms i.e. RATS-HM, AINN-BPSO, MOABCQ. From results it is evident that our proposed ATSIA3C outperforms existing task schedulers by improving makespan by 70.49%. Resource cost is improved by 77.42%. Energy Consumption is improved over compared algorithms 74.24% in multi cloud environment by proposed ATSIA3C.

PP-MARL: Efficient Privacy-Preserving Multi-Agent Reinforcement Learning for Cooperative Intelligence in Communications

PP-MARL: Efficient Privacy-Preserving Multi-Agent Reinforcement Learning for Cooperative Intelligence in Communications

Efficient and scalable reinforcement learning for large-scale network control

The primary challenge in the development of large-scale artificial intelligence (AI) systems lies in achieving scalable decision-making—extending the AI models while maintaining sufficient performance. Existing research indicates that distributed AI can improve scalability by decomposing complex tasks and distributing them across collaborative nodes. However, previous technologies suffered from compromised real-world applicability and scalability due to the massive requirement of communication and sampled data. Here we develop a model-based decentralized policy optimization framework, which can be efficiently deployed in multi-agent systems. By leveraging local observation through the agent-level topological decoupling of global dynamics, we prove that this decentralized mechanism achieves accurate estimations of global information. Importantly, we further introduce model learning to reinforce the optimal policy for monotonic improvement with a limited amount of sampled data. Empirical results on diverse scenarios show the superior scalability of our approach, particularly in real-world systems with hundreds of agents, thereby paving the way for scaling up AI systems.

Optimal operational planning of a bio-fuelled cogeneration plant: Integration of sparse nonlinear dynamics identification and deep reinforcement learning

This paper presents a novel data-driven approach for short-term operational planning of a cogeneration plant. The proposed methodology utilizes sparse identification of nonlinear dynamics (SINDy) to extract a dynamic model of heat generation from operational data. This model is then employed to simulate the plant dynamics during the training of a reinforcement learning (RL) agent, enabling online stochastic optimization of the production plan in real-time. The incorporation of SINDy enhances the accuracy of capturing the plant's nonlinear dynamics and significantly improves the computational speed of plant simulations, enabling efficient RL agent training within a reasonable timeframe. The performance of operational planning with the RL agent is compared to that of dynamic programming, a widely used method in the literature. The evaluation metric encompasses energy efficiency, unmet demands, and wasted heat. The comparison investigates the effectiveness of RL and dynamic programming under various scenarios with different qualities of energy demand forecasts. The RL agent exhibits robustness and notably improves the operational planning performance, particularly when faced with uncertain energy demands in the environment. Furthermore, the findings show that the RL agent, trained on a school building data, could successfully perform planning tasks for a hotel building, indicating the transferability of learned planning knowledge across different cogeneration use cases.

Efficient and stable deep reinforcement learning: selective priority timing entropy

Efficient and stable deep reinforcement learning: selective priority timing entropy

Efficient Offline Reinforcement Learning With Relaxed Conservatism.

Offline reinforcement learning (RL) aims at learning an optimal policy from a static offline data set, without interacting with the environment. However, the theoretical understanding of the existing offline RL methods needs further studies, among which the conservatism of the learned Q-function and the learned policy is a major issue. In this article, we propose a simple and efficient offline RL with relaxed conservatism (ORL-RC) framework for addressing this concern by learning a Q-function that is close to the true Q-function under the learned policy. The conservatism of learned Q-functions and policies of offline RL methods is analyzed. The analysis results support that the conservatism can lead to policy performance degradation. We establish the convergence results of the proposed ORL-RC, and the bounds of learned Q-functions with and without sampling errors, respectively, suggesting that the gap between the learned Q-function and the true Q-function can be reduced by executing the conservative policy improvement. A practical implementation of ORL-RC is presented and the experimental results on the D4RL benchmark suggest that ORL-RC exhibits superior performance and substantially outperforms existing state-of-the-art offline RL methods.

Efficient Reinforcement Learning for 3D Jumping Monopods.

We consider a complex control problem: making a monopod accurately reach a target with a single jump. The monopod can jump in any direction at different elevations of the terrain. This is a paradigm for a much larger class of problems, which are extremely challenging and computationally expensive to solve using standard optimization-based techniques. Reinforcement learning (RL) is an interesting alternative, but an end-to-end approach in which the controller must learn everything from scratch can be non-trivial with a sparse-reward task like jumping. Our solution is to guide the learning process within an RL framework leveraging nature-inspired heuristic knowledge. This expedient brings widespread benefits, such as a drastic reduction of learning time, and the ability to learn and compensate for possible errors in the low-level execution of the motion. Our simulation results reveal a clear advantage of our solution against both optimization-based and end-to-end RL approaches.

Efficient deep reinforcement learning strategies for active flow control based on physics-informed neural networks

Reducing the reliance on intrusive flow probes is a critical task in active flow control based on deep reinforcement learning (DRL). Although a scarcity of flow data captured by probes adversely impacts the control proficiency of the DRL agent, leading to suboptimal flow modulation, minimizing the use of redundant probes significantly reduces the overall implementation costs, making the control strategy more economically viable. In this paper, we propose an active flow control method based on physics-informed DRL. This method integrates a physics-informed neural network into the DRL framework, harnessing the inherent physical characteristics of the flow field using strategically placed probes. We analyze the impact of probe placement, probe quantity, and DRL agent sampling strategies on the fidelity of flow predictions and the efficacy of flow control. Using the wake control of a two-dimensional cylinder flow with a Reynolds number of 100 as a case study, we position a specific number of flow probes within the flow field to gather pertinent information. When benchmarked against traditional DRL techniques, the results are unequivocal: in terms of training efficiency, physics-informed DRL reduces the training cycle by up to 30 rounds. Furthermore, by decreasing the number of flow probes in the flow field from 164 to just 4, the physics-based DRL achieves superior drag reduction through more precise control. Notably, compared to traditional DRL control, the drag reduction effect is enhanced by a significant 6%.

E-DBRL: efficient double broad reinforcement learning for adaptive traffic signal control

E-DBRL: efficient double broad reinforcement learning for adaptive traffic signal control

Multi-objective task offloading for highly dynamic heterogeneous Vehicular Edge Computing: An efficient reinforcement learning approach

Vehicular Edge Computing (VEC) provides a flexible distributed computing paradigm for offloading computations to the vehicular network, which can effectively solve the problem of limited vehicle computing resources and meet the on-vehicle computing requests of users. However, the conflict of interest between vehicle users and service providers leads to the need to consider a variety of conflict optimization goals for computing offloading, and the dynamic nature of vehicle networks, such as vehicle mobility and time-varying network conditions, make the offloading effectiveness of vehicle computing requests and the adaptability to complex VEC scenarios challenging. To address these challenges, this paper proposes a multi-objective optimization model suitable for computational offloading of dynamic heterogeneous VEC networks. By formulating the dynamic multi-objective computational offloading problem as a multi-objective Markov Decision Process (MOMDP), this paper designs a novel multi-objective reinforcement learning algorithm EMOTO, which aims to minimize the average task execution delay and average vehicle energy consumption, and maximize the revenue of service providers. In this paper, a preference priority sampling module is proposed, and a model-augmented environment estimator is introduced to learn the environmental model for multi-objective optimization, so as to solve the problem that the agent is difficult to learn steadily caused by the highly dynamic change of VEC environment, thus to effectively realize the joint optimization of multiple objectives and improve the decision-making accuracy and efficiency of the algorithm. Experiments show that EMOTO has superior performance on multiple optimization objectives compared with advanced multi-objective reinforcement learning algorithms. In addition, the algorithm shows robustness when applied to different environmental settings and better adapting to highly dynamic environments, and balancing the conflict of interest between vehicle users and service providers.

Reward prediction error neurons implement an efficient code for reward.

We use efficient coding principles borrowed from sensory neuroscience to derive the optimal neural population to encode a reward distribution. We show that the responses of dopaminergic reward prediction error neurons in mouse and macaque are similar to those of the efficient code in the following ways: the neurons have a broad distribution of midpoints covering the reward distribution; neurons with higher thresholds have higher gains, more convex tuning functions and lower slopes; and their slope is higher when the reward distribution is narrower. Furthermore, we derive learning rules that converge to the efficient code. The learning rule for the position of the neuron on the reward axis closely resembles distributional reinforcement learning. Thus, reward prediction error neuron responses may be optimized to broadcast an efficient reward signal, forming a connection between efficient coding and reinforcement learning, two of the most successful theories in computational neuroscience.

An efficient intrusive deep reinforcement learning framework for OpenFOAM

An efficient intrusive deep reinforcement learning framework for OpenFOAM

Sample-efficient reinforcement learning with knowledge-embedded hybrid model for optimal control of mining industry

The froth flotation process is a cost-effective and widely employed method for mineral separation. A core challenge is to maximize mineral recovery while maintaining a specified minimum concentrate grade. This requires precise control of aeration and slurry level and overcoming disturbances. The rapid advancements in reinforcement learning present a promising approach for controlling froth flotation. However, reinforcement learning suffers from sample inefficiency, which significantly hampers its application to real-world problems. In this research, we proposed an innovative sample-efficient model-based reinforcement learning algorithm to enhance flotation performance by directly leveraging the dynamics of the slurry phase. Our proposed algorithm involves the construction of a hybrid model, comprising a physical model and a data residual model, which effectively learns the underlying dynamics of the flotation process during the interaction between the reinforcement learning agent and process. The physical model integrates domain knowledge into the hybrid model to expedite the training process and enhance the interpretability and generalizability of the hybrid model. To capture uncertainty and address unmodeled aspects of the physical model, we employ an ensemble data residual model. Actor and critic are augmented with fuzzy representation modules based on fuzzy logic inference to improve the learning capacity of the networks and the multi-head critic is applied to reduce overestimation biases and enhance training stability. Case studies demonstrate that, compared to the baseline algorithm, our proposed algorithm requires merely 86.8% of the samples employed by conventional model-based reinforcement learning algorithm and improves the long-term return by at least 12.0%, underscoring the role of domain knowledge in facilitating efficient reinforcement learning.

Learning with sparse reward in a gap junction network inspired by the insect mushroom body.

Animals can learn in real-life scenarios where rewards are often only available when a goal is achieved. This 'distal' or 'sparse' reward problem remains a challenge for conventional reinforcement learning algorithms. Here we investigate an algorithm for learning in such scenarios, inspired by the possibility that axo-axonal gap junction connections, observed in neural circuits with parallel fibres such as the insect mushroom body, could form a resistive network. In such a network, an active node represents the task state, connections between nodes represent state transitions and their connection to actions, and current flow to a target state can guide decision making. Building on evidence that gap junction weights are adaptive, we propose that experience of a task can modulate the connections to form a graph encoding the task structure. We demonstrate that the approach can be used for efficient reinforcement learning under sparse rewards, and discuss whether it is plausible as an account of the insect mushroom body.

Optimizing Energy Consumption in 5G HetNets: A Coordinated Approach for Multi-Level Picocell Sleep Mode with Q-Learning

Cell standby, particularly picocell sleep mode (SM), is a prominent strategy for reducing energy consumption in 5G networks. The emergence of multi-state sleep states necessitates new optimization approaches. This paper proposes a novel energy optimization strategy for 5G heterogeneous networks (HetNets) that leverages macrocell-picocell coordination and machine learning. The proposed strategy focuses on managing the four available picocell sleep states. The picocell manages the first three states using the Q-learning algorithm, an efficient reinforcement learning technique. The associated macrocell based on picocell energy efficiency controls the final, deeper sleep state. This hierarchical approach leverages localized and network-wide control strengths for optimal energy savings. By capitalizing on macrocell-picocell coordination and machine learning, this work presents a promising solution for achieving significant energy reduction in 5G HetNets while maintaining network performance.