Log in

Relevant bibliographies by topics / Actor-critic learning / Journal articles

To see the other types of publications on this topic, follow the link: Actor-critic learning.

Journal articles on the topic 'Actor-critic learning'

Author: Grafiati

Published: 2 June 2025

Last updated: 31 July 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the top 50 journal articles for your research on the topic 'Actor-critic learning.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.

1

Zheng, Liyuan, Tanner Fiez, Zane Alumbaugh, Benjamin Chasnov, and Lillian J. Ratliff. "Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 8 (2022): 9217–24. http://dx.doi.org/10.1609/aaai.v36i8.20908.

Full text

Abstract:

The hierarchical interaction between the actor and critic in actor-critic based reinforcement learning algorithms naturally lends itself to a game-theoretic interpretation. We adopt this viewpoint and model the actor and critic interaction as a two-player general-sum game with a leader-follower structure known as a Stackelberg game. Given this abstraction, we propose a meta-framework for Stackelberg actor-critic algorithms where the leader player follows the total derivative of its objective instead of the usual individual gradient. From a theoretical standpoint, we develop a policy gradient t

APA, Harvard, Vancouver, ISO, and other styles

2

Kim, Jong-Ho, Dae-Sung Kang, and Joo-Young Park. "Robot Locomotion via RLS-based Actor-Critic Learning." Journal of Fuzzy Logic and Intelligent Systems 15, no. 7 (2005): 893–98. http://dx.doi.org/10.5391/jkiis.2005.15.7.893.

Full text

APA, Harvard, Vancouver, ISO, and other styles

3

Wang, Fulin, Bozhao Wang, and Wentao Tang. "Reinforcement Learning Optimization Scheduling of Micro-integrated Energy Systems Under Uncertain Factors." Journal of Physics: Conference Series 3012, no. 1 (2025): 012089. https://doi.org/10.1088/1742-6596/3012/1/012089.

Full text

Abstract:

Abstract This study focuses on the optimal scheduling of integrated energy systems under uncertain factors. In view of the impact of uncertainty in wind power and photovoltaic output on system scheduling, an optimization strategy based on the improved Soft Actor-Critic algorithm is proposed. This challenge is met by simulating uncertainty data and improving the Soft Actor-Critic objective function. A mathematical model of a micro-integrated energy system is constructed in this paper, covering equipment and uncertainty models, and an optimal scheduling model is constructed based on the Soft Act

APA, Harvard, Vancouver, ISO, and other styles

4

Grondman, Ivo, Maarten Vaandrager Lucian Busoniu, Robert Babuska, and Erik Schuitema. "Actor-Critic Control with Reference Model Learning." IFAC Proceedings Volumes 44, no. 1 (2011): 14723–28. http://dx.doi.org/10.3182/20110828-6-it-1002.00759.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

Chen, Ruidong, and Jesse H. Goldberg. "Actor-critic reinforcement learning in the songbird." Current Opinion in Neurobiology 65 (December 2020): 1–9. http://dx.doi.org/10.1016/j.conb.2020.08.005.

Full text

APA, Harvard, Vancouver, ISO, and other styles

6

Wang, Xue-Song, Yu-Hu Cheng, and Jian-Qiang Yi. "A fuzzy Actor–Critic reinforcement learning network." Information Sciences 177, no. 18 (2007): 3764–81. http://dx.doi.org/10.1016/j.ins.2007.03.012.

Full text

APA, Harvard, Vancouver, ISO, and other styles

7

Wang, Mingyi, Jianhao Tang, Haoli Zhao, Zhenni Li, and Shengli Xie. "Automatic Compression of Neural Network with Deep Reinforcement Learning Based on Proximal Gradient Method." Mathematics 11, no. 2 (2023): 338. http://dx.doi.org/10.3390/math11020338.

Full text

Abstract:

In recent years, the model compression technique is very effective for deep neural network compression. However, many existing model compression methods rely heavily on human experience to explore a compression strategy between network structure, speed, and accuracy, which is usually suboptimal and time-consuming. In this paper, we propose a framework for automatically compressing models through the actor–critic structured deep reinforcement learning (DRL) which interacts with each layer in the neural network, where the actor network determines the compression strategy and the critic network e

APA, Harvard, Vancouver, ISO, and other styles

8

TAHAMI, EHSAN, AMIR HOMAYOUN JAFARI, and ALI FALLAH. "APPLICATION OF AN EVOLUTIONARY ACTOR–CRITIC REINFORCEMENT LEARNING METHOD FOR THE CONTROL OF A THREE-LINK MUSCULOSKELETAL ARM DURING A REACHING MOVEMENT." Journal of Mechanics in Medicine and Biology 13, no. 02 (2013): 1350040. http://dx.doi.org/10.1142/s0219519413500401.

Full text

Abstract:

In this paper, the control of a planar three-link musculoskeletal arm by using a revolutionary actor–critic reinforcement learning (RL) method during a reaching movement to a stationary target is presented. The arm model used in this study included three skeletal links (wrist, forearm, and upper arm), three joints (wrist, elbow, and shoulder without redundancy), and six non-linear monoarticular muscles (with redundancy), which were based on the Hill model. The learning control system was composed of actor, critic, and genetic algorithm (GA) parts. Two single-layer neural networks were used for

APA, Harvard, Vancouver, ISO, and other styles

9

Kong, Lingzhi. "A Vehicle Adaptive Cruise Control Method Based on Deep Reinforcement Learning Algorithm." Applied and Computational Engineering 125, no. 1 (2025): 102–9. https://doi.org/10.54254/2755-2721/2025.20196.

Full text

Abstract:

Adaptive cruise control (ACC) is an upgrade to the traditional cruise control system in vehicles. This paper presents an adaptive cruise control method based on the Deep Deterministic Policy Gradient (DDPG) algorithm. The Actor network computes actions based on the current state, adding noise to enhance exploration. The Critic network computes the Q-value of the current state-action pair. The Actor target network and Critic target network compute the Q-value of the next state-action pair. The gradient descent method is used to minimize the loss function of the Critic network, which includes th

APA, Harvard, Vancouver, ISO, and other styles

10

Hatakeyama, Hiroyuki, Shingo Mabu, Kotaro Hirasawa, and Jinglu Hu. "Genetic Network Programming with Actor-Critic." Journal of Advanced Computational Intelligence and Intelligent Informatics 11, no. 1 (2007): 79–86. http://dx.doi.org/10.20965/jaciii.2007.p0079.

Full text

Abstract:

A new graph-based evolutionary algorithm named “Genetic Network Programming, GNP” has been already proposed. GNP represents its solutions as graph structures, which can improve the expression ability and performance. In addition, GNP with Reinforcement Learning (GNP-RL) was proposed a few years ago. Since GNP-RL can do reinforcement learning during task execution in addition to evolution after task execution, it can search for solutions efficiently. In this paper, GNP with Actor-Critic (GNP-AC) which is a new type of GNP-RL is proposed. Originally, GNP deals with discrete information, but GNP-

APA, Harvard, Vancouver, ISO, and other styles

11

Hafez, Muhammad Burhan, Cornelius Weber, Matthias Kerzel, and Stefan Wermter. "Deep intrinsically motivated continuous actor-critic for efficient robotic visuomotor skill learning." Paladyn, Journal of Behavioral Robotics 10, no. 1 (2019): 14–29. http://dx.doi.org/10.1515/pjbr-2019-0005.

Full text

Abstract:

Abstract In this paper, we present a new intrinsically motivated actor-critic algorithm for learning continuous motor skills directly from raw visual input. Our neural architecture is composed of a critic and an actor network. Both networks receive the hidden representation of a deep convolutional autoencoder which is trained to reconstruct the visual input, while the centre-most hidden representation is also optimized to estimate the state value. Separately, an ensemble of predictive world models generates, based on its learning progress, an intrinsic reward signal which is combined with the

APA, Harvard, Vancouver, ISO, and other styles

12

Kong, Minseok, and Jungmin So. "Empirical Analysis of Automated Stock Trading Using Deep Reinforcement Learning." Applied Sciences 13, no. 1 (2023): 633. http://dx.doi.org/10.3390/app13010633.

Full text

Abstract:

There are several automated stock trading programs using reinforcement learning, one of which is an ensemble strategy. The main idea of the ensemble strategy is to train DRL agents and make an ensemble with three different actor–critic algorithms: Advantage Actor–Critic (A2C), Deep Deterministic Policy Gradient (DDPG), and Proximal Policy Optimization (PPO). This novel idea was the concept mainly used in this paper. However, we did not stop there, but we refined the automated stock trading in two areas. First, we made another DRL-based ensemble and employed it as a new trading agent. We named

APA, Harvard, Vancouver, ISO, and other styles

13

Wu, Menghao, Yanbin Gao, Alexander Jung, Qiang Zhang, and Shitong Du. "The Actor-Dueling-Critic Method for Reinforcement Learning." Sensors 19, no. 7 (2019): 1547. http://dx.doi.org/10.3390/s19071547.

Full text

Abstract:

Model-free reinforcement learning is a powerful and efficient machine-learning paradigm which has been generally used in the robotic control domain. In the reinforcement learning setting, the value function method learns policies by maximizing the state-action value (Q value), but it suffers from inaccurate Q estimation and results in poor performance in a stochastic environment. To mitigate this issue, we present an approach based on the actor-critic framework, and in the critic branch we modify the manner of estimating Q-value by introducing the advantage function, such as dueling network, w

APA, Harvard, Vancouver, ISO, and other styles

14

Liu, Dr Wei Jun, and Yiming Chen. "Dynamic Multi-Objective Recommendation Via Discrete Soft Actor-Critic." International Research Journal of Library and Information Sciences 2, no. 5 (2025): 1–5. https://doi.org/10.55640/irjlis-v02i05-01.

Full text

Abstract:

Modern recommender systems often need to optimize multiple conflicting objectives, such as accuracy, diversity, and novelty. This paper proposes a novel approach, Dynamic Multi-Objective Recommendation via Discrete Soft Actor-Critic (DMOR-DSAC), to address this challenge. DMOR-DSAC employs a reinforcement learning framework with a discrete action space, utilizing the Soft Actor-Critic algorithm to learn a policy that dynamically balances these objectives. Experimental results on benchmark datasets demonstrate the effectiveness of DMOR-DSAC in achieving superior multi-objective performance comp

APA, Harvard, Vancouver, ISO, and other styles

15

Hernandez-Leal, Pablo, Bilal Kartal, and Matthew E. Taylor. "Agent Modeling as Auxiliary Task for Deep Reinforcement Learning." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 15, no. 1 (2019): 31–37. http://dx.doi.org/10.1609/aiide.v15i1.5221.

Full text

Abstract:

In this paper we explore how actor-critic methods in deep reinforcement learning, in particular Asynchronous Advantage Actor-Critic (A3C), can be extended with agent modeling. Inspired by recent works on representation learning and multiagent deep reinforcement learning, we propose two architectures to perform agent modeling: the first one based on parameter sharing, and the second one based on agent policy features. Both architectures aim to learn other agents’ policies as auxiliary tasks, besides the standard actor (policy) and critic (values). We performed experiments in both cooperative an

APA, Harvard, Vancouver, ISO, and other styles

16

Ding, Feng, Guanfeng Ma, Zhikui Chen, Jing Gao, and Peng Li. "Averaged Soft Actor-Critic for Deep Reinforcement Learning." Complexity 2021 (April 1, 2021): 1–16. http://dx.doi.org/10.1155/2021/6658724.

Full text

Abstract:

With the advent of the era of artificial intelligence, deep reinforcement learning (DRL) has achieved unprecedented success in high-dimensional and large-scale artificial intelligence tasks. However, the insecurity and instability of the DRL algorithm have an important impact on its performance. The Soft Actor-Critic (SAC) algorithm uses advanced functions to update the policy and value network to alleviate some of these problems. However, SAC still has some problems. In order to reduce the error caused by the overestimation of SAC, we propose a new SAC algorithm called Averaged-SAC. By averag

APA, Harvard, Vancouver, ISO, and other styles

17

Grondman, I., M. Vaandrager, L. Busoniu, R. Babuska, and E. Schuitema. "Efficient Model Learning Methods for Actor–Critic Control." IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 42, no. 3 (2012): 591–602. http://dx.doi.org/10.1109/tsmcb.2011.2170565.

Full text

APA, Harvard, Vancouver, ISO, and other styles

18

Muse, David, and Stefan Wermter. "Actor-Critic Learning for Platform-Independent Robot Navigation." Cognitive Computation 1, no. 3 (2009): 203–20. http://dx.doi.org/10.1007/s12559-009-9021-z.

Full text

APA, Harvard, Vancouver, ISO, and other styles

19

Lan, Xuejing, Zhifeng Tan, Tao Zou, and Wenbiao Xu. "CACLA-Based Trajectory Tracking Guidance for RLV in Terminal Area Energy Management Phase." Sensors 21, no. 15 (2021): 5062. http://dx.doi.org/10.3390/s21155062.

Full text

Abstract:

This paper focuses on the trajectory tracking guidance problem for the Terminal Area Energy Management (TAEM) phase of the Reusable Launch Vehicle (RLV). Considering the continuous state and action space of this guidance problem, the Continuous Actor–Critic Learning Automata (CACLA) is applied to construct the guidance strategy of RLV. Two three-layer neuron networks are used to model the critic and actor of CACLA, respectively. The weight vectors of the critic are updated by the model-free Temporal Difference (TD) learning algorithm, which is improved by eligibility trace and momentum factor.

APA, Harvard, Vancouver, ISO, and other styles

20

Sun, Yuezhongyi, and Boyu Yang. "A priority experience replay actor-critic algorithm using self-attention mechanism for strategy optimization of discrete problems." PeerJ Computer Science 10 (June 28, 2024): e2161. http://dx.doi.org/10.7717/peerj-cs.2161.

Full text

Abstract:

In the dynamic field of deep reinforcement learning, the self-attention mechanism has been increasingly recognized. Nevertheless, its application in discrete problem domains has been relatively limited, presenting complex optimization challenges. This article introduces a pioneering deep reinforcement learning algorithm, termed Attention-based Actor-Critic with Priority Experience Replay (A2CPER). A2CPER combines the strengths of self-attention mechanisms with the Actor-Critic framework and prioritized experience replay to enhance policy formulation for discrete problems. The algorithm’s archi

APA, Harvard, Vancouver, ISO, and other styles

21

Yue, Han, Jiapeng Liu, Dongmei Tian, and Qin Zhang. "A Novel Anti-Risk Method for Portfolio Trading Using Deep Reinforcement Learning." Electronics 11, no. 9 (2022): 1506. http://dx.doi.org/10.3390/electronics11091506.

Full text

Abstract:

In the past decade, the application of deep reinforcement learning (DRL) in portfolio management has attracted extensive attention. However, most classical RL algorithms do not consider the exogenous and noise of financial time series data, which may lead to treacherous trading decisions. To address this issue, we propose a novel anti-risk portfolio trading method based on deep reinforcement learning (DRL). It consists of a stacked sparse denoising autoencoder (SSDAE) network and an actor–critic based reinforcement learning (RL) agent. SSDAE will carry out off-line training first, while the de

APA, Harvard, Vancouver, ISO, and other styles

22

Seo, Kanghyeon, and Jihoon Yang. "Differentially Private Actor and Its Eligibility Trace." Electronics 9, no. 9 (2020): 1486. http://dx.doi.org/10.3390/electronics9091486.

Full text

Abstract:

We present a differentially private actor and its eligibility trace in an actor-critic approach, wherein an actor takes actions directly interacting with an environment; however, the critic estimates only the state values that are obtained through bootstrapping. In other words, the actor reflects the more detailed information about the sequence of taken actions on its parameter than the critic. Moreover, their corresponding eligibility traces have the same properties. Therefore, it is necessary to preserve the privacy of an actor and its eligibility trace while training on private or sensitive

APA, Harvard, Vancouver, ISO, and other styles

23

Kim, Jung-Hyun, Yong-Hoon Choi, and Min-Suk Kim. "Reinforcement Learning Maximized-Actor-Critic(MAC) Method Based on Policy-Gradient." Journal of Korea Multimedia Society 27, no. 3 (2024): 455–63. http://dx.doi.org/10.9717/kmms.2024.27.3.455.

Full text

APA, Harvard, Vancouver, ISO, and other styles

24

Garrido-Castañeda, Sergio Isahí, Juan Irving Vasquez, and Mayra Antonio-Cruz. "Coverage Path Planning Using Actor–Critic Deep Reinforcement Learning." Sensors 25, no. 5 (2025): 1592. https://doi.org/10.3390/s25051592.

Full text

Abstract:

One of the main capabilities a mobile robot must demonstrate is the ability to explore its environment. The core challenge in exploration lies in planning the route to fully cover the environment. Despite recent advances, this problem remains unsolved. This study proposes an approach to address the coverage path planning problem, where the mobile robot is tasked with exploring and completely covering a terrain using a deep reinforcement learning framework. The environment is divided into cells, with obstacles designated as prohibited areas. The robot is trained using two state-of-the-art reinf

APA, Harvard, Vancouver, ISO, and other styles

25

Su, Jianyu, Stephen Adams, and Peter Beling. "Value-Decomposition Multi-Agent Actor-Critics." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 13 (2021): 11352–60. http://dx.doi.org/10.1609/aaai.v35i13.17353.

Full text

Abstract:

The exploitation of extra state information has been an active research area in multi-agent reinforcement learning (MARL). QMIX represents the joint action-value using a non-negative function approximator and achieves the best performance on the StarCraft II micromanagement testbed, a common MARL benchmark. However, our experiments demonstrate that, in some cases, QMIX performs sub-optimally with the A2C framework, a training paradigm that promotes algorithm training efficiency. To obtain a reasonable trade-off between training efficiency and algorithm performance, we extend value-decompositio

APA, Harvard, Vancouver, ISO, and other styles

26

Zhang, Haifeng, Weizhe Chen, Zeren Huang, et al. "Bi-Level Actor-Critic for Multi-Agent Coordination." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (2020): 7325–32. http://dx.doi.org/10.1609/aaai.v34i05.6226.

Full text

Abstract:

Coordination is one of the essential problems in multi-agent systems. Typically multi-agent reinforcement learning (MARL) methods treat agents equally and the goal is to solve the Markov game to an arbitrary Nash equilibrium (NE) when multiple equilibra exist, thus lacking a solution for NE selection. In this paper, we treat agents unequally and consider Stackelberg equilibrium as a potentially better convergence point than Nash equilibrium in terms of Pareto superiority, especially in cooperative environments. Under Markov games, we formally define the bi-level reinforcement learning problem

APA, Harvard, Vancouver, ISO, and other styles

27

Zhu, Qingling, Xiaoqiang Wu, Qiuzhen Lin, and Wei-Neng Chen. "Two-Stage Evolutionary Reinforcement Learning for Enhancing Exploration and Exploitation." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 18 (2024): 20892–900. http://dx.doi.org/10.1609/aaai.v38i18.30079.

Full text

Abstract:

The integration of Evolutionary Algorithm (EA) and Reinforcement Learning (RL) has emerged as a promising approach for tackling some challenges in RL, such as sparse rewards, lack of exploration, and brittle convergence properties. However, existing methods often employ actor networks as individuals of EA, which may constrain their exploratory capabilities, as the entire actor population will stop evolution when the critic network in RL falls into local optimal. To alleviate this issue, this paper introduces a Two-stage Evolutionary Reinforcement Learning (TERL) framework that maintains a popu

APA, Harvard, Vancouver, ISO, and other styles

28

Doya, Kenji. "Reinforcement Learning in Continuous Time and Space." Neural Computation 12, no. 1 (2000): 219–45. http://dx.doi.org/10.1162/089976600300015961.

Full text

Abstract:

This article presents a reinforcement learning framework for continuous-time dynamical systems without a priori discretization of time, state, and action. Basedonthe Hamilton-Jacobi-Bellman (HJB) equation for infinite-horizon, discounted reward problems, we derive algorithms for estimating value functions and improving policies with the use of function approximators. The process of value function estimation is formulated as the minimization of a continuous-time form of the temporal difference (TD) error. Update methods based on backward Euler approximation and exponential eligibility traces ar

APA, Harvard, Vancouver, ISO, and other styles

29

Zhang, Xianxia, Runbin Yan, Gang Zhou, Lufeng Wang, and Bing Wang. "Online Three-Dimensional Fuzzy Reinforcement Learning Modeling for Nonlinear Distributed Parameter Systems." Electronics 13, no. 21 (2024): 4217. http://dx.doi.org/10.3390/electronics13214217.

Full text

Abstract:

Distributed parameter systems (DPSs) frequently appear in industrial manufacturing processes, with complex characteristics such as time–space coupling, nonlinearity, infinite dimension, uncertainty and so on, which is full of challenges to the modeling of the system. At present, most DPS modeling methods are offline. When the internal parameters or external environment of DPS change, the offline model is incapable of accurately representing the dynamic attributes of the real system. Establishing an online model for DPS that accurately reflects the real-time dynamics of the system is very impor

APA, Harvard, Vancouver, ISO, and other styles

30

Saglam, Baturay, Furkan B. Mutlu, Dogan C. Cicek, and Suleyman S. Kozat. "Actor Prioritized Experience Replay." Journal of Artificial Intelligence Research 78 (November 16, 2023): 639–72. http://dx.doi.org/10.1613/jair.1.14819.

Full text

Abstract:

A widely-studied deep reinforcement learning (RL) technique known as Prioritized Experience Replay (PER) allows agents to learn from transitions sampled with non-uniform probability proportional to their temporal-difference (TD) error. Although it has been shown that PER is one of the most crucial components for the overall performance of deep RL methods in discrete action domains, many empirical studies indicate that it considerably underperforms off-policy actor-critic algorithms. We theoretically show that actor networks cannot be effectively trained with transitions that have large TD erro

APA, Harvard, Vancouver, ISO, and other styles

31

Zhu, Ye, and Xiaowen Gong. "Single-Loop Federated Actor-Critic across Heterogeneous Environments." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 21 (2025): 23054–62. https://doi.org/10.1609/aaai.v39i21.34469.

Full text

Abstract:

Federated reinforcement learning (FRL) has emerged as a promising paradigm, enabling multiple agents to collaborate and learn a shared policy adaptable across heterogeneous environments. Among the various reinforcement learning (RL) algorithms, the actor-critic (AC) algorithm stands out for its low variance and high sample efficiency. However, little to nothing is known theoretically about AC in a federated manner, especially each agent interacts with a potentially different environment. The lack of such results is attributed to various technical challenges: a two-level structure illustrating

APA, Harvard, Vancouver, ISO, and other styles

32

ARSLAN, FURKAN, and REYHAN AYDOĞAN. "Actor-critic reinforcement learning for bidding in bilateral negotiation." Turkish Journal of Electrical Engineering and Computer Sciences 30, no. 5 (2022): 1695–714. http://dx.doi.org/10.55730/1300-0632.3899.

Full text

APA, Harvard, Vancouver, ISO, and other styles

33

Wang, Yu, Jack Stokes, and Mady Marinescu. "Actor Critic Deep Reinforcement Learning for Neural Malware Control." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 01 (2020): 1005–12. http://dx.doi.org/10.1609/aaai.v34i01.5449.

Full text

Abstract:

In addition to using signatures, antimalware products also detect malicious attacks by evaluating unknown files in an emulated environment, i.e. sandbox, prior to execution on a computer's native operating system. During emulation, a file cannot be scanned indefinitely, and antimalware engines often set the number of instructions to be executed based on a set of heuristics. These heuristics only make the decision of when to halt emulation using partial information leading to the execution of the file for either too many or too few instructions. Also this method is vulnerable if the attackers l

APA, Harvard, Vancouver, ISO, and other styles

34

Han, Minghao, Lixian Zhang, Jun Wang, and Wei Pan. "Actor-Critic Reinforcement Learning for Control With Stability Guarantee." IEEE Robotics and Automation Letters 5, no. 4 (2020): 6217–24. http://dx.doi.org/10.1109/lra.2020.3011351.

Full text

APA, Harvard, Vancouver, ISO, and other styles

35

Li, Tongyue, Dianxi Shi, Songchang Jin, Zhen Wang, Huanhuan Yang, and Yang Chen. "Multi-Agent Hierarchical Graph Attention Actor–Critic Reinforcement Learning." Entropy 27, no. 1 (2024): 4. https://doi.org/10.3390/e27010004.

Full text

Abstract:

Multi-agent systems often face challenges such as elevated communication demands, intricate interactions, and difficulties in transferability. To address the issues of complex information interaction and model scalability, we propose an innovative hierarchical graph attention actor–critic reinforcement learning method. This method naturally models the interactions within a multi-agent system as a graph, employing hierarchical graph attention to capture the complex cooperative and competitive relationships among agents, thereby enhancing their adaptability to dynamic environments. Specifically,

APA, Harvard, Vancouver, ISO, and other styles

36

Chen, Yi, Meiwei Lin, Zhuo Yu, Weihong Sun, Weiguo Fu, and Liang He. "Enhancing cotton irrigation with distributional actor–critic reinforcement learning." Agricultural Water Management 307 (February 2025): 109194. https://doi.org/10.1016/j.agwat.2024.109194.

Full text

APA, Harvard, Vancouver, ISO, and other styles

37

Konda, Vijaymohan R., and Vivek S. Borkar. "Actor-Critic--Type Learning Algorithms for Markov Decision Processes." SIAM Journal on Control and Optimization 38, no. 1 (1999): 94–123. http://dx.doi.org/10.1137/s036301299731669x.

Full text

APA, Harvard, Vancouver, ISO, and other styles

38

Heredia, Paulo C., and Shaoshuai Mou. "Distributed Multi-Agent Reinforcement Learning by Actor-Critic Method." IFAC-PapersOnLine 52, no. 20 (2019): 363–68. http://dx.doi.org/10.1016/j.ifacol.2019.12.182.

Full text

APA, Harvard, Vancouver, ISO, and other styles

39

Yang, Meiyi, Nianbo Liu, Lin Zuo, et al. "Dynamic Charging Scheme Problem With Actor–Critic Reinforcement Learning." IEEE Internet of Things Journal 8, no. 1 (2021): 370–80. http://dx.doi.org/10.1109/jiot.2020.3005598.

Full text

APA, Harvard, Vancouver, ISO, and other styles

40

Panov, A. I., and L. A. Ugadiarov. "A World Model for Actor–Critic in Reinforcement Learning." Pattern Recognition and Image Analysis 33, no. 3 (2023): 467–77. http://dx.doi.org/10.1134/s1054661823030379.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

Ma, Zhongcui, Dandan Lai, Jianxiang Zhu, and Yaxin Peng. "Offline Robustness of Distributional Actor-Critic Ensemble Reinforcement Learning." Advances in Pure Mathematics 15, no. 04 (2025): 269–90. https://doi.org/10.4236/apm.2025.154013.

Full text

APA, Harvard, Vancouver, ISO, and other styles

42

Arvindhan, M., and D. Rajesh Kumar. "Adaptive Resource Allocation in Cloud Data Centers using Actor-Critical Deep Reinforcement Learning for Optimized Load Balancing." International Journal on Recent and Innovation Trends in Computing and Communication 11, no. 5s (2023): 310–18. http://dx.doi.org/10.17762/ijritcc.v11i5s.6671.

Full text

Abstract:

This paper proposes a deep reinforcement learning-based actor-critic method for efficient resource allocation in cloud computing. The proposed method uses an actor network to generate the allocation strategy and a critic network to evaluate the quality of the allocation. The actor and critic networks are trained using a deep reinforcement learning algorithm to optimize the allocation strategy. The proposed method is evaluated using a simulation-based experimental study, and the results show that it outperforms several existing allocation methods in terms of resource utilization, energy efficie

APA, Harvard, Vancouver, ISO, and other styles

43

Zhou, Chengmin, Bingding Huang, and Pasi Fränti. "A review of motion planning algorithms for intelligent robots." Journal of Intelligent Manufacturing 33, no. 2 (2021): 387–424. http://dx.doi.org/10.1007/s10845-021-01867-z.

Full text

Abstract:

AbstractPrinciples of typical motion planning algorithms are investigated and analyzed in this paper. These algorithms include traditional planning algorithms, classical machine learning algorithms, optimal value reinforcement learning, and policy gradient reinforcement learning. Traditional planning algorithms investigated include graph search algorithms, sampling-based algorithms, interpolating curve algorithms, and reaction-based algorithms. Classical machine learning algorithms include multiclass support vector machine, long short-term memory, Monte-Carlo tree search and convolutional neur

APA, Harvard, Vancouver, ISO, and other styles

44

Nauman, Michal, and Marek Cygan. "Decoupled Policy Actor-Critic: Bridging Pessimism and Risk Awareness in Reinforcement Learning." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 18 (2025): 19633–41. https://doi.org/10.1609/aaai.v39i18.34162.

Full text

Abstract:

Actor-Critic (AC) algorithms like SAC and TD3 were shown to perform well in a variety of continuous-action tasks. However, the theoretical basis for the pessimistic objectives these algorithms employ remains unestablished, raising questions about the specific class of policies they are implementing. In this work, we apply the expected utility hypothesis, a fundamental concept in economics, to illustrate that both pessimistic and non-pessimistic RL objectives can be interpreted through expected utility maximization using an exponential utility function. This approach reveals that pessimistic po

APA, Harvard, Vancouver, ISO, and other styles

45

Saglam, Baturay, Furkan Mutlu, Dogan Cicek, and Suleyman Kozat. "Actor Prioritized Experience Replay (Abstract Reprint)." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 20 (2024): 22710. http://dx.doi.org/10.1609/aaai.v38i20.30610.

Full text

Abstract:

A widely-studied deep reinforcement learning (RL) technique known as Prioritized Experience Replay (PER) allows agents to learn from transitions sampled with non-uniform probability proportional to their temporal-difference (TD) error. Although it has been shown that PER is one of the most crucial components for the overall performance of deep RL methods in discrete action domains, many empirical studies indicate that it considerably underperforms off-policy actor-critic algorithms. We theoretically show that actor networks cannot be effectively trained with transitions that have large TD erro

APA, Harvard, Vancouver, ISO, and other styles

46

Ma, Jungmok. "Military Decision Support with Actor and Critic Reinforcement Learning Agents." Defence Science Journal 74, no. 3 (2024): 389–98. http://dx.doi.org/10.14429/dsj.74.18864.

Full text

Abstract:

While the recent advanced military operational concept requires an intelligent support of command and control, Reinforcement Learning (RL) has not been actively studied in the military domain. This study points out the limitations of RL for military applications from literature review and aims at improving the understanding of RL for military decision support under the limitations. Most of all, the black box characteristic of Deep RL makes the internal process difficult to understand in addition to complex simulation tools. A scalable weapon selection RL framework is built which can be solved

APA, Harvard, Vancouver, ISO, and other styles

47

Panda, Prashansa, and Shalabh Bhatnagar. "Two-Timescale Critic-Actor for Average Reward MDPs with Function Approximation." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 19 (2025): 19813–20. https://doi.org/10.1609/aaai.v39i19.34182.

Full text

Abstract:

Several recent works have focused on carrying out non-asymptotic convergence analyses for AC algorithms. Recently, a two-timescale critic-actor algorithm has been presented for the discounted cost setting in the look-up table case where the timescales of the actor and the critic are reversed and only asymptotic convergence shown. In our work, we present the first two-timescale critic-actor algorithm with function approximation in the long-run average reward setting and present the first finite-time non-asymptotic as well as asymptotic convergence analysis for such a scheme. We obtain optimal l

APA, Harvard, Vancouver, ISO, and other styles

48

Hwang, Ha Jun, Jaeyeon Jang, Jongkwan Choi, Jung Ho Bae, Sung Ho Kim, and Chang Ouk Kim. "Stepwise Soft Actor–Critic for UAV Autonomous Flight Control." Drones 7, no. 9 (2023): 549. http://dx.doi.org/10.3390/drones7090549.

Full text

Abstract:

Despite the growing demand for unmanned aerial vehicles (UAVs), the use of conventional UAVs is limited, as most of them require being remotely operated by a person who is not within the vehicle’s field of view. Recently, many studies have introduced reinforcement learning (RL) to address hurdles for the autonomous flight of UAVs. However, most previous studies have assumed overly simplified environments, and thus, they cannot be applied to real-world UAV operation scenarios. To address the limitations of previous studies, we propose a stepwise soft actor–critic (SeSAC) algorithm for efficient

APA, Harvard, Vancouver, ISO, and other styles

49

Syafiqah Lagiman, Abu Ubaidah Shamsudin, Zubair Adil Soomro, Mohamad Hafiz Abu Bakar, Ruzairi Abdul Rahim, and Carl John Salaan. "A Soft Actor-Critic Approach to Complex Dynamic Flight Control for a Flying Firefighter Robot with Water-Jet Propulsion." Journal of Advanced Research in Applied Sciences and Engineering Technology 34, no. 2 (2023): 271–86. http://dx.doi.org/10.37934/araset.34.2.271286.

Full text

Abstract:

Most of the robots nowadays become more intelligent in line AI technology are being applied in industry. Deep Reinforcement Learning (DRL) is involves gaining knowledge by making errors and fixing them. Hence, the robot will learn from mistakes and keep improving by process. Deep Reinforcement Learning is a kind of machine learning method that focuses on teaching models to act in ways that maximize rewards in an environment. Since the algorithm receives feedback in the form of rewards or consequences for its actions, this is often accomplished through trial and error. Soft Actor Critic (SAC) i

APA, Harvard, Vancouver, ISO, and other styles

50

Zhang, Zuozhen, Junzhong Ji, and Jinduo Liu. "MetaRLEC: Meta-Reinforcement Learning for Discovery of Brain Effective Connectivity." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 9 (2024): 10261–69. http://dx.doi.org/10.1609/aaai.v38i9.28892.

Full text

Abstract:

In recent years, the discovery of brain effective connectivity (EC) networks through computational analysis of functional magnetic resonance imaging (fMRI) data has gained prominence in neuroscience and neuroimaging. However, owing to the influence of diverse factors during data collection and processing, fMRI data typically exhibits high noise and limited sample characteristics, consequently leading to suboptimal performance of current methods. In this paper, we propose a novel brain effective connectivity discovery method based on meta-reinforcement learning, called MetaRLEC. The method main

APA, Harvard, Vancouver, ISO, and other styles

We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!