Yige Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yige Huang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Fu-Chun Zheng
School of Electronic and Information Engineering, Harbin Institute of Technology (ShenZhen), Shenzhen, China
13 shared publications - Yanxiang Jiang
National Mobile Communications Research Laboratory, Southeast University, Nanjing, China
13 shared publications - Pengcheng Zhu
National Mobile Communications Research Laboratory, Southeast University, Nanjing, China
6 shared publications - Xiaohu You
Southeast University
5 shared publications - Dongming Wang
Southeast University
4 shared publications - Dusit Niyato
Nanyang technological university, Singapore, Singapore
3 shared publications
Latest Publications
- 4 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 7958-7968
Energy Consumption Minimization in MEC-Empowered CF-mMIMO System Based on Multi-Agent Deep Reinforcement Learning
To satisfy strict latency requirements, we consider a mobile edge computing (MEC)-empowered cell-free massive multiple-input multiple-output (CF-mMIMO) system. To minimize the total energy consumption of user ends under low-latency constraints, an optimization problem is formulated that combines the optimization of offloading decisions, power allocation, and computing resource allocation. By considering the distributed architecture of CF-mMIMO, a partially centralized training multi-agent proximal policy optimization (PC-MAPPO) algorithm is proposed. This algorithm enables the coexistence of both centralized and distributed training in the system, reducing computational complexity while saving communications overhead. Meanwhile, the scheme allows for the existence of different types of agents to jointly optimize the actions of users and access points (APs). The simulation results show that the proposed algorithm reduces energy consumption compared to the considered traditional solutions, while having lower computational complexity and better scalability.
- 4 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 7958-7968
Energy Consumption Minimization in MEC-Empowered CF-mMIMO System Based on Multi-Agent Deep Reinforcement Learning
To satisfy strict latency requirements, we consider a mobile edge computing (MEC)-empowered cell-free massive multiple-input multiple-output (CF-mMIMO) system. To minimize the total energy consumption of user ends under low-latency constraints, an optimization problem is formulated that combines the optimization of offloading decisions, power allocation, and computing resource allocation. By considering the distributed architecture of CF-mMIMO, a partially centralized training multi-agent proximal policy optimization (PC-MAPPO) algorithm is proposed. This algorithm enables the coexistence of both centralized and distributed training in the system, reducing computational complexity while saving communications overhead. Meanwhile, the scheme allows for the existence of different types of agents to jointly optimize the actions of users and access points (APs). The simulation results show that the proposed algorithm reduces energy consumption compared to the considered traditional solutions, while having lower computational complexity and better scalability.
- 26 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 25 (15361276) , 14166-14182
Energy-Efficient Resource Orchestration for URLLC in Cell-Free RANs via GNNs With Reliability Enforcement
Future wireless networks aim to deliver ultra-reliable and low-latency services while containing their rapidly growing energy footprint. In a cell-free radio access network (CF-RAN), this objective translates into a tightly coupled optimisation over access point (AP) activation, user association, precoding design and virtual-CPU provisioning, all under finite-blocklength reliability constraints. We build a detailed power model that includes radio hardware, fronthaul and load-dependent computing, then recast the resulting energy efficiency problem as a mixed-integer second-order cone programming using a tight surrogate for decoding-error probability. A sparsity-promoting convex–concave solver can reach near-optimal solutions but must be run for every channel realisation, making real-time use impractical. To overcome this limitation, we propose a graph neural network (GNN) that represents CF-RAN as a heterogeneous AP-to-user graph, predicts precoding vectors, rates and soft association probabilities in a single forward pass, and then applies a lightweight reliability-enforcement layer to remove any residual violations. Simulation results show that, whenever the constraints are feasible, the learned solver achieves comparable energy efficiency as the optimization-based baseline while operating with only a single-pass inference step per channel realization.
- 26 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 25 (15361276) , 14166-14182
Energy-Efficient Resource Orchestration for URLLC in Cell-Free RANs via GNNs With Reliability Enforcement
Future wireless networks aim to deliver ultra-reliable and low-latency services while containing their rapidly growing energy footprint. In a cell-free radio access network (CF-RAN), this objective translates into a tightly coupled optimisation over access point (AP) activation, user association, precoding design and virtual-CPU provisioning, all under finite-blocklength reliability constraints. We build a detailed power model that includes radio hardware, fronthaul and load-dependent computing, then recast the resulting energy efficiency problem as a mixed-integer second-order cone programming using a tight surrogate for decoding-error probability. A sparsity-promoting convex–concave solver can reach near-optimal solutions but must be run for every channel realisation, making real-time use impractical. To overcome this limitation, we propose a graph neural network (GNN) that represents CF-RAN as a heterogeneous AP-to-user graph, predicts precoding vectors, rates and soft association probabilities in a single forward pass, and then applies a lightweight reliability-enforcement layer to remove any residual violations. Simulation results show that, whenever the constraints are feasible, the learned solver achieves comparable energy efficiency as the optimization-based baseline while operating with only a single-pass inference step per channel realization.
- 25 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 25 (15361276) , 1301-1316
Learning-Driven Rate-Splitting for Energy-Efficient Hardware-Impaired Cell-Free URLLC Systems
Efficient resource allocation in hardware-impaired cell-free systems is critical for achieving the stringent requirements of ultra-reliable low-latency communication (URLLC) while maintaining energy efficiency (EE). Traditional optimization-based approaches face scalability issues, while existing learning-based methods struggle to adapt to varying network structures and the complexities of hardware impairments. In this work, we address these challenges by incorporating rate-splitting multiple access (RSMA) into cell-free systems and designing a graph neural network (GNN)-based framework. First, we propose a method leveraging explicit channel state information to optimize precoding for both common and private streams under rate, power, and latency constraints. Next, we further develop an end-to-end approach that bypasses channel estimation by directly using raw pilot signals for joint feature extraction and optimization. Finally, we introduce a pilot-free method that processes distorted message-passing information from real channels, reducing communications overhead while enhancing adaptability to practical conditions. Through extensive simulations, we validate the proposed methods, demonstrating significant improvements in EE, along with insights into their computational complexity and scalability in diverse system configurations.
- 25 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 25 (15361276) , 1301-1316
Learning-Driven Rate-Splitting for Energy-Efficient Hardware-Impaired Cell-Free URLLC Systems
Efficient resource allocation in hardware-impaired cell-free systems is critical for achieving the stringent requirements of ultra-reliable low-latency communication (URLLC) while maintaining energy efficiency (EE). Traditional optimization-based approaches face scalability issues, while existing learning-based methods struggle to adapt to varying network structures and the complexities of hardware impairments. In this work, we address these challenges by incorporating rate-splitting multiple access (RSMA) into cell-free systems and designing a graph neural network (GNN)-based framework. First, we propose a method leveraging explicit channel state information to optimize precoding for both common and private streams under rate, power, and latency constraints. Next, we further develop an end-to-end approach that bypasses channel estimation by directly using raw pilot signals for joint feature extraction and optimization. Finally, we introduce a pilot-free method that processes distorted message-passing information from real channels, reducing communications overhead while enhancing adaptability to practical conditions. Through extensive simulations, we validate the proposed methods, demonstrating significant improvements in EE, along with insights into their computational complexity and scalability in diverse system configurations.
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 73 (8) , 5935-5949
Multi-Agent Reinforcement Learning Based Cooperative Caching With Low Entropy Communications in Fog-RANs
In this paper, we investigate a cooperative edge caching problem in the fog radio access networks (F-RANs). In order to obtain the globally optimal caching caching strategy that minimizes the content transmission delay and maximizes communication efficiency, we propose a multi-agent reinforcement learning based cooperative caching policy with low entropy communications. First, we propose a double deep Q network (DDQN) based caching policy by taking into account the non-deterministic polynomial hard (NP-hard) aspect of this cooperative caching optimization problem. Then, we extend the state transition model of Markov Decision Process (MDP) under the single agent system into the Stochastic Game (SG) one under the multi-agent system. By employing the DDQN in each agent, the agents can learn and make the global decision for caching. For utilizing the cooperation resources of fog access points (F-APs), the interaction of information is introduced to exchange the historical cache records of cooperative F-APs. However, the information in the interaction may require lower entropy in the fiber link. Therefore, the information entropy is largely reduced to improve the communication efficiency by quantifying the information. Finally, due to the non-computable gradient of information entropy, we apply a pseudo gradient descent method to approximate the gradient descent in the local model. Simulation results show that our policy achieves better performance in terms of reducing the transmission delay and improving the cooperation among F-APs compared to the benchmark policies. Additionally, it is demonstrated that the proposed policy improves communication efficiency without compromising the performance of cooperative caching.
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 73 (8) , 5935-5949
Multi-Agent Reinforcement Learning Based Cooperative Caching With Low Entropy Communications in Fog-RANs
In this paper, we investigate a cooperative edge caching problem in the fog radio access networks (F-RANs). In order to obtain the globally optimal caching caching strategy that minimizes the content transmission delay and maximizes communication efficiency, we propose a multi-agent reinforcement learning based cooperative caching policy with low entropy communications. First, we propose a double deep Q network (DDQN) based caching policy by taking into account the non-deterministic polynomial hard (NP-hard) aspect of this cooperative caching optimization problem. Then, we extend the state transition model of Markov Decision Process (MDP) under the single agent system into the Stochastic Game (SG) one under the multi-agent system. By employing the DDQN in each agent, the agents can learn and make the global decision for caching. For utilizing the cooperation resources of fog access points (F-APs), the interaction of information is introduced to exchange the historical cache records of cooperative F-APs. However, the information in the interaction may require lower entropy in the fiber link. Therefore, the information entropy is largely reduced to improve the communication efficiency by quantifying the information. Finally, due to the non-computable gradient of information entropy, we apply a pseudo gradient descent method to approximate the gradient descent in the local model. Simulation results show that our policy achieves better performance in terms of reducing the transmission delay and improving the cooperation among F-APs compared to the benchmark policies. Additionally, it is demonstrated that the proposed policy improves communication efficiency without compromising the performance of cooperative caching.
- 26 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 24 (3) , 2279-2296
Effective Energy Efficiency of Cell-Free mMIMO Systems for URLLC With Probabilistic Delay Bounds and Finite Blocklength Communications
Ultra-Reliable and Low-Latency Communications (URLLC) is essential for sixth generation communications, with Cell-Free massive Multiple-input-Multiple-Output (CF mMIMO) being a promising architecture to support these demands. This paper addresses the challenge of optimizing energy efficiency in CF mMIMO systems for URLLC, focusing on the probabilistic delay bounds and finite blocklength communications. We propose a theoretical framework that considers tail distributions to evaluate extreme reliability and latency requirements, instead of relying on asymptotic analysis. In particular, a closed-form expression for the signal-to-interference-plus-noise ratio (SINR) distribution is derived, accommodating imperfections in channel state information caused by pilot contamination. Then, the paper also presents a comprehensive reliability analysis, incorporating both delay violation probability and average decoding error probability, utilizing stochastic network calculus for accurate statistical modeling. Finally, an innovative power control algorithm is proposed to maximize effective energy efficiency (EEE), the ratio of the effective data rate to total power consumption, while meeting stringent Quality-of-Service (QoS) constraints and power limits. Extensive simulations validate the theoretical framework and the efficacy of the proposed algorithm, demonstrating its ability to enhance EEE in various scenarios and providing insights into the interplay between EEE, delay, and reliability metrics.
- 26 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 24 (3) , 2279-2296
Effective Energy Efficiency of Cell-Free mMIMO Systems for URLLC With Probabilistic Delay Bounds and Finite Blocklength Communications
Ultra-Reliable and Low-Latency Communications (URLLC) is essential for sixth generation communications, with Cell-Free massive Multiple-input-Multiple-Output (CF mMIMO) being a promising architecture to support these demands. This paper addresses the challenge of optimizing energy efficiency in CF mMIMO systems for URLLC, focusing on the probabilistic delay bounds and finite blocklength communications. We propose a theoretical framework that considers tail distributions to evaluate extreme reliability and latency requirements, instead of relying on asymptotic analysis. In particular, a closed-form expression for the signal-to-interference-plus-noise ratio (SINR) distribution is derived, accommodating imperfections in channel state information caused by pilot contamination. Then, the paper also presents a comprehensive reliability analysis, incorporating both delay violation probability and average decoding error probability, utilizing stochastic network calculus for accurate statistical modeling. Finally, an innovative power control algorithm is proposed to maximize effective energy efficiency (EEE), the ratio of the effective data rate to total power consumption, while meeting stringent Quality-of-Service (QoS) constraints and power limits. Extensive simulations validate the theoretical framework and the efficacy of the proposed algorithm, demonstrating its ability to enhance EEE in various scenarios and providing insights into the interplay between EEE, delay, and reliability metrics.
- 8 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 29 (1) , 70-74
A Multi-Agent DRL Method for Distributed Energy-Efficient Association and Hybrid Precoding in mmWave Cell-Free Massive MIMO Systems
In this letter, we investigate a distributed design integrating user-centric association with local sub-connected hybrid precoding in mmWave cell-free massive MIMO (CF-mMIMO) systems, aiming to maximize the long-term global energy efficiency (EE) under quality-of-service and power budget constraints. The joint optimization problem is formulated as a Markov Game problem and a novel weighted critic update multi-agent twin-delayed deep deterministic policy gradient (WCU-MATD3) algorithm is proposed to solve it, which promotes cooperation among access point agents and reduces power consumption in front-haul links. The results show that the proposed WCU-MATD3 algorithm significantly improves the global EE and the trade-off between spectral efficiency (SE) and EE, providing a practical and stable distributed collaboration framework for dynamic distributed environments.
- 8 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 29 (1) , 70-74
A Multi-Agent DRL Method for Distributed Energy-Efficient Association and Hybrid Precoding in mmWave Cell-Free Massive MIMO Systems
In this letter, we investigate a distributed design integrating user-centric association with local sub-connected hybrid precoding in mmWave cell-free massive MIMO (CF-mMIMO) systems, aiming to maximize the long-term global energy efficiency (EE) under quality-of-service and power budget constraints. The joint optimization problem is formulated as a Markov Game problem and a novel weighted critic update multi-agent twin-delayed deep deterministic policy gradient (WCU-MATD3) algorithm is proposed to solve it, which promotes cooperation among access point agents and reduces power consumption in front-haul links. The results show that the proposed WCU-MATD3 algorithm significantly improves the global EE and the trade-off between spectral efficiency (SE) and EE, providing a practical and stable distributed collaboration framework for dynamic distributed environments.
- 4 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 14 (1) , 98-102
Energy Consumption Optimization in Cell-Free Massive MIMO Systems With Hybrid Energy Supply
With the development of communications technology and the massive deployment of communications equipment, the energy burden on communications networks is becoming increasingly severe. Energy harvesting (EH) technology can be used to collect green energy from the environment for access points (APs) in a cell-free massive multiple-input multiple-output (CF-mMIMO) system. Due to the hybrid power supply, different APs receive energy unevenly, which may result in green energy waste and thus higher grid energy consumption. With regard to this, we allow energy transmission through the smart grid in our system and formulate a problem of minimizing grid energy consumption while satisfying the quality of service (QoS) demands of users, where energy management and power control (PC) are taken into consideration jointly. Then, we propose a scheme based on the soft actor-critic (SAC) algorithm to intelligently schedule network resources, whose reward function is designed to achieve QoS guarantees and minimize grid power consumption. Simulation results show that our method has significant potential to reduce grid energy consumption in uneven energy distribution scenarios and offers a runtime advantage over iterative algorithms.
- 4 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 14 (1) , 98-102
Energy Consumption Optimization in Cell-Free Massive MIMO Systems With Hybrid Energy Supply
With the development of communications technology and the massive deployment of communications equipment, the energy burden on communications networks is becoming increasingly severe. Energy harvesting (EH) technology can be used to collect green energy from the environment for access points (APs) in a cell-free massive multiple-input multiple-output (CF-mMIMO) system. Due to the hybrid power supply, different APs receive energy unevenly, which may result in green energy waste and thus higher grid energy consumption. With regard to this, we allow energy transmission through the smart grid in our system and formulate a problem of minimizing grid energy consumption while satisfying the quality of service (QoS) demands of users, where energy management and power control (PC) are taken into consideration jointly. Then, we propose a scheme based on the soft actor-critic (SAC) algorithm to intelligently schedule network resources, whose reward function is designed to achieve QoS guarantees and minimize grid power consumption. Simulation results show that our method has significant potential to reduce grid energy consumption in uneven energy distribution scenarios and offers a runtime advantage over iterative algorithms.
- 27 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (2) , 2826-2839
Access Points Cooperation Based Secretive Coded Caching in Fog Radio Access Networks
In this study, we address the issue of secretive coded caching in fog radio access networks (F-RANs). Our approach involves a hierarchical placement scheme during the placement phase, which efficiently leverages the cache resources of both fog access points (F-APs) and users while adhering to secrecy constraints. In the delivery phase, we employ an access points cooperation based delivery scheme that maximizes the cooperative transmission capability among multiple F-APs. By integrating the placement and delivery schemes, we propose an access points cooperation based secretive coded caching scheme that minimize the sum rate. We further derive a closed-form expression for the worst-case sum rate and obtain an information theretic lower bound on the sum rate by using cut-set arguments. Our analysis reveals that the proposed scheme achieves the information theoretic lower bound within a factor that depends on the number of F-APs. Additionally, we analyze the decodability and secrecy aspects of the proposed coded caching scheme. Simulation results demonstrate that when the cache capacity of each F-AP is large, the performance of our proposed scheme approaches the theoretical optimum.
- 27 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (2) , 2826-2839
Access Points Cooperation Based Secretive Coded Caching in Fog Radio Access Networks
In this study, we address the issue of secretive coded caching in fog radio access networks (F-RANs). Our approach involves a hierarchical placement scheme during the placement phase, which efficiently leverages the cache resources of both fog access points (F-APs) and users while adhering to secrecy constraints. In the delivery phase, we employ an access points cooperation based delivery scheme that maximizes the cooperative transmission capability among multiple F-APs. By integrating the placement and delivery schemes, we propose an access points cooperation based secretive coded caching scheme that minimize the sum rate. We further derive a closed-form expression for the worst-case sum rate and obtain an information theretic lower bound on the sum rate by using cut-set arguments. Our analysis reveals that the proposed scheme achieves the information theoretic lower bound within a factor that depends on the number of F-APs. Additionally, we analyze the decodability and secrecy aspects of the proposed coded caching scheme. Simulation results demonstrate that when the cache capacity of each F-AP is large, the performance of our proposed scheme approaches the theoretical optimum.
- 4 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (1) , 1238-1251
Edge Cooperation Based Coded Caching in Fog Radio Access Networks
In this paper, we investigate edge cooperation based coded caching in fog radio access networks (F-RANs). Initially, we propose a cooperative coded caching scheme which utilizes cooperation between fog access points (F-APs) to facilitate efficient multicasting. In this scheme, to achieve a higher caching gain, we design the tiered placement strategy; to reduce the multicasting gain losses as well as the delay and energy costs of multicasting, we propose the differential encoding based delivery strategy. Moreover, in order to better fully utilize the edge-computing capabilities of F-RANs, neighboring F-APs are clustered to enable multiple F-APs to utilize the mixed caching scheme to collaboratively serve one user, thereby leveraging the potential gains in the physical layer cooperation. The inter-cluster cooperative coded caching scheme and the inner-cluster mixed caching scheme compose the comprehensive caching scheme that is analyzed and optimized in terms of delay and energy efficiency (EE). Simulation results show that our proposed cooperative coded caching scheme can provide up to 46% savings in the transmission cost compared to the conventional group-based coded caching scheme, and the comprehensive caching scheme can achieve significant flexibility in delay-sensitive and EE-sensitive scenarios.
- 4 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (1) , 1238-1251
Edge Cooperation Based Coded Caching in Fog Radio Access Networks
In this paper, we investigate edge cooperation based coded caching in fog radio access networks (F-RANs). Initially, we propose a cooperative coded caching scheme which utilizes cooperation between fog access points (F-APs) to facilitate efficient multicasting. In this scheme, to achieve a higher caching gain, we design the tiered placement strategy; to reduce the multicasting gain losses as well as the delay and energy costs of multicasting, we propose the differential encoding based delivery strategy. Moreover, in order to better fully utilize the edge-computing capabilities of F-RANs, neighboring F-APs are clustered to enable multiple F-APs to utilize the mixed caching scheme to collaboratively serve one user, thereby leveraging the potential gains in the physical layer cooperation. The inter-cluster cooperative coded caching scheme and the inner-cluster mixed caching scheme compose the comprehensive caching scheme that is analyzed and optimized in terms of delay and energy efficiency (EE). Simulation results show that our proposed cooperative coded caching scheme can provide up to 46% savings in the transmission cost compared to the conventional group-based coded caching scheme, and the comprehensive caching scheme can achieve significant flexibility in delay-sensitive and EE-sensitive scenarios.
- 8 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 28 (9) , 2086-2090
Energy-Efficient Joint AP Selection and Power Control in Cell-Free Massive MIMO Systems: A Hybrid Action Space-DRL Approach
In this letter, we investigate the problem of joint access point (AP) selection and power control in Cell-free massive MIMO (CF-mMIMO) networks, aiming at maximizing energy efficiency (EE) under a sum spectral efficiency (SSE) requirement. Given the limitations of separate optimizations due to strong couplings between AP selection and power control, a novel deep reinforcement learning (DRL) approach with hybrid action space is proposed. Simulation results show that our proposed algorithm achieves low-dimensional actions by embedding parameters and can achieve higher EE with lower complexity.
- 8 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 28 (9) , 2086-2090
Energy-Efficient Joint AP Selection and Power Control in Cell-Free Massive MIMO Systems: A Hybrid Action Space-DRL Approach
In this letter, we investigate the problem of joint access point (AP) selection and power control in Cell-free massive MIMO (CF-mMIMO) networks, aiming at maximizing energy efficiency (EE) under a sum spectral efficiency (SSE) requirement. Given the limitations of separate optimizations due to strong couplings between AP selection and power control, a novel deep reinforcement learning (DRL) approach with hybrid action space is proposed. Simulation results show that our proposed algorithm achieves low-dimensional actions by embedding parameters and can achieve higher EE with lower complexity.