Dear Editor,This letter presents a new transfer learning framework for the deep multi-agent reinforcement learning(DMARL) to reduce the convergence difficulty and training time when applying DMARL to a new scenario [1...
详细信息
Dear Editor,This letter presents a new transfer learning framework for the deep multi-agent reinforcement learning(DMARL) to reduce the convergence difficulty and training time when applying DMARL to a new scenario [1], [2].
Learning the accurate dynamics of robotic systems directly from the trajectory data is currently a prominent research *** physics-enforced networks,exemplified by Hamiltonian neural networks and Lagrangian neural netw...
详细信息
Learning the accurate dynamics of robotic systems directly from the trajectory data is currently a prominent research *** physics-enforced networks,exemplified by Hamiltonian neural networks and Lagrangian neural networks,demonstrate proficiency in modeling ideal physical systems,but face limitations when applied to systems with uncertain non-conservative dynamics due to the inherent constraints of the conservation laws *** this paper,we present a novel augmented deep Lagrangian network,which seamlessly integrates a deep Lagrangian network with a standard deep *** fusion aims to effectively model uncertainties that surpass the limitations of conventional Lagrangian *** proposed network is applied to learn inverse dynamics model of two multi-degree manipulators including a 6-dof UR-5 robot and a 7-dof SARCOS manipulator under *** experimental results clearly demonstrate that our approach exhibits superior modeling precision and enhanced physical credibility.
The latest trends in the research field of single-view human reconstruction are devoted to learning deep implicit functions constrained by explicit body shape priors. Despite the remarkable performance improvements co...
详细信息
Federated learning (FL) is a promising decentralized machine learning approach that enables multiple distributed clients to train a model jointly while keeping their data private. However, in real-world scenarios, the...
详细信息
Federated learning (FL) is a promising decentralized machine learning approach that enables multiple distributed clients to train a model jointly while keeping their data private. However, in real-world scenarios, the supervised training data stored in local clients inevitably suffer from imperfect annotations, resulting in subjective, inconsistent and biased labels. These noisy labels can harm the collaborative aggregation process of FL by inducing inconsistent decision boundaries. Unfortunately, few attempts have been made towards noise-tolerant federated learning, with most of them relying on the strategy of transmitting overhead messages to assist noisy labels detection and correction, which increases the communication burden as well as privacy risks. In this paper, we propose a simple yet effective method for noise-tolerant FL based on the well-established co-training framework. Our method leverages the inherent discrepancy in the learning ability of the local and global models in FL, which can be regarded as two complementary views. By iteratively exchanging samples with their high confident predictions, the two models “teach each other” to suppress the influence of noisy labels. The proposed scheme enjoys the benefit of overhead cost-free and can serve as a robust and efficient baseline for noise-tolerant federated learning. Experimental results demonstrate that our method outperforms existing approaches, highlighting the superiority of our method.
Traffic congestion is the root cause of various social and economic problems like longer travel times, increased pollution, and fuel or energy consumption. Addressing the issue is becoming increasingly crucial with ri...
详细信息
In the Maximum Independent Set of Hyperrectangles problem, we are given a set of n (possibly overlapping) d-dimensional axis-aligned hyperrectangles, and the goal is to find a subset of non-overlapping hyperrectangles...
详细信息
This paper focuses on the optimal output synchronization control problem of heterogeneous multiagent systems(HMASs) subject to nonidentical communication delays by a reinforcement learning *** with existing studies as...
详细信息
This paper focuses on the optimal output synchronization control problem of heterogeneous multiagent systems(HMASs) subject to nonidentical communication delays by a reinforcement learning *** with existing studies assuming that the precise model of the leader is globally or distributively accessible to all or some of the followers, the leader's precise dynamical model is entirely inaccessible to all the followers in this paper. A data-based learning algorithm is first proposed to reconstruct the leader's unknown system matrix online. A distributed predictor subject to communication delays is further devised to estimate the leader's state, where interaction delays are allowed to be nonidentical. Then, a learning-based local controller, together with a discounted performance function, is projected to reach the optimal output synchronization. Bellman equations and game algebraic Riccati equations are constructed to learn the optimal solution by developing a model-based reinforcement learning(RL) algorithm online without solving regulator equations, which is followed by a model-free off-policy RL algorithm to relax the requirement of all agents' dynamics faced by the model-based RL algorithm. The optimal tracking control of HMASs subject to unknown leader dynamics and communication delays is shown to be solvable under the proposed RL algorithms. Finally, the effectiveness of theoretical analysis is verified by numerical simulations.
Semantic segmentation plays an important role in computer perception tasks. Integrating the rich details of RGB images with the illumination robustness of thermal infrared (TIR) images is a promising approach for achi...
详细信息
Semantic segmentation plays an important role in computer perception tasks. Integrating the rich details of RGB images with the illumination robustness of thermal infrared (TIR) images is a promising approach for achieving reliable semantic scene understanding. Current approaches for RGB-Thermal semantic segmentation often overlook the unique characteristics exhibited by each modality at different encoding layers and underutilize the complementary information between the two modalities during decoding. To acquire complementary cross-modality encoding and decoding features, we propose a multi-branch differential bidirectional fusion network known as MDBFNet. Firstly, it models the dependencies between the modality-specific characteristics and the different encoding layers, and designs a TIR-led detail enhancement module (TDE) and an RGB-led semantic enhancement module (RSE) to guide distinguishable fusion for different layer features. Secondly, a three-branch fusion decoder with three supervision (TFDS) is proposed to thoroughly explore the complementary decoding features between two modalities. Experiments on MFNet and PST900 datasets show that our method surpasses state-of-the-art methods by a clear margin. IEEE
Control frameworks for legged robots often rely on accurate dynamic models. However, these models often proves to be inaccurate due to factors such as mechanical wear and tear, and unforeseen changes such as the addit...
详细信息
暂无评论