Almost all multi-agent reinforcement learning algorithms without communication follow the principle of centralized training with decentralized execution. During centralized training, agents can be guided by the same signals, such as the global state. During decentralized execution, however, agents lack the shared signal. Inspired by viewpoint invariance and contrastive learning, we propose consensus learning for cooperative multi-agent reinforcement learning in this paper. Although based on local observations, different agents can infer the same consensus in discrete space. During decentralized execution, we feed the inferred consensus as an explicit input to the network of agents, thereby developing their spirit of cooperation. Our proposed method can be extended to various multi-agent reinforcement learning algorithms. Moreover, we carry out them on some fully cooperative tasks and get convincing results.
Coarse-grained models have proven helpful for simulating complex systems over long timescales to provide molecular insights into various processes. Methodologies for systematic parameterization of the underlying energy function, or force field that describes the interactions among different components of the system are of great interest for ensuring simulation accuracy. We present a new method, potential contrasting, to enable efficient learning of force fields that can accurately reproduce the conformational distribution produced with all-atom simulations. Potential contrasting generalizes the noise contrastive estimation method with umbrella sampling to better learn the complex energy landscape of molecular systems. When applied to the Trp-cage protein, we found that the technique produces force fields that thoroughly capture the thermodynamics of the folding process despite the use of only $\alpha$-Carbons in the coarse-grained model. We further showed that potential contrasting could be applied over large datasets that combine the conformational ensembles of many proteins to ensure the transferability of coarse-grained force fields. We anticipate potential contrasting to be a powerful tool for building general-purpose coarse-grained force fields.
Recently, model-based agents have achieved better performance compared with model-free ones using the same computational budget and training time in single-agent environments. However, due to the complexity of multi-agent systems, it is very difficult to learn the model of the environment. When model-based methods are applied to multi-agent tasks, the significant compounding error may hinder the learning process. In this paper, we propose an implicit model-based multi-agent reinforcement learning method based on value decomposition methods. Under this method, agents can interact with the learned virtual environment and evaluate the current state value according to imagined future states, which makes agents have foresight. Our method can be applied to any multi-agent value decomposition method. The experimental results show that our method improves the sample efficiency in partially observable Markov decision process domains.
The performance of deep reinforcement learning (DRL) in single-agent video games is astounding due to its benefits in dealing with sequential decision-making challenges. However, researchers have extra difficulties while working with video games in multi-agent environments. One of the most pressing issues presently being addressed is how to create sufficient collaboration between different agents in a scenario with numerous agents. To address this issue, we propose a novel algorithm based on the actor-critic method, which adapts the hypergraph structure of agents and employs hypergraph convolution to complete information feature extraction and representation between agents, resulting in efficient collaboration. Based on distinct generating methods of hypergraph structure, HGAC and ATT-HGAC algorithms are given. We demonstrate the advantages of our approach over other existing methods. Ablation and visualization studies also confirm the relevance of each component of the algorithm.
Along with current multi-scale based detectors, Feature Aggregation and Enhancement (FAE) modules have shown superior performance gains for cutting-edge object detection. However, these hand-crafted FAE modules show inconsistent improvements on face detection, which is mainly due to the significant distribution difference between its training and applying corpus, COCO vs. WIDER Face. To tackle this problem, we essentially analyse the effect of data distribution, and consequently propose to search an effective FAE architecture, termed AutoFAE by a differentiable architecture search, which outperforms all existing FAE modules in face detection with a considerable margin. Upon the found AutoFAE and existing backbones, a supernet is further built and trained, which automatically obtains a family of detectors under the different complexity constraints. Extensive experiments conducted on popular benchmarks, WIDER Face and FDDB, demonstrate the state-of-the-art performance-efficiency trade-off for the proposed automatic and scalable face detector (ASFD) family. In particular, our strong ASFD-D6 outperforms the best competitor with AP 96.7/96.2/92.1 on WIDER Face test, and the lightweight ASFD-D0 costs about 3.1 ms, more than 320 FPS, on the V100 GPU with VGA-resolution images.
Recent studies show that depression can be partially reflected from human facial attributes. Since facial attributes have various data structure and carry different information, existing approaches fail to specifically consider the optimal way to extract depression-related features from each of them, as well as investigates the best fusion strategy. In this paper, we propose to extend Neural Architecture Search (NAS) technique for designing an optimal model for multiple facial attributes-based depression recognition, which can be efficiently and robustly implemented in a small dataset. Our approach first conducts a warmer up step to the feature extractor of each facial attribute, aiming to largely reduce the search space and providing customized architecture, where each feature extractor can be either a Convolution Neural Networks (CNN) or Graph Neural Networks (GNN). Then, we conduct an end-to-end architecture search for all feature extractors and the fusion network, allowing the complementary depression cues to be optimally combined with less redundancy. The experimental results on AVEC 2016 dataset show that the model explored by our approach achieves breakthrough performance with 27\% and 30\% RMSE and MAE improvements over the existing state-of-the-art. In light of these findings, this paper provides solid evidences and a strong baseline for applying NAS to time-series data-based mental health analysis.
In the current salient object detection network, the most popular method is using U-shape structure. However, the massive number of parameters leads to more consumption of computing and storage resources which are not feasible to deploy on the limited memory device. Some others shallow layer network will not maintain the same accuracy compared with U-shape structure and the deep network structure with more parameters will not converge to a global minimum loss with great speed. To overcome all of these disadvantages, we proposed a new deep convolution network architecture with three contributions: (1) using smaller convolution neural networks (CNNs) to compress the model in our improved salient object features compression and reinforcement extraction module (ISFCREM) to reduce parameters of the model. (2) introducing channel attention mechanism in ISFCREM to weigh different channels for improving the ability of feature representation. (3) applying a new optimizer to accumulate the long-term gradient information during training to adaptively tune the learning rate. The results demonstrate that the proposed method can compress the model to 1/3 of the original size nearly without losing the accuracy and converging faster and more smoothly on six widely used datasets of salient object detection compared with the others models. Our code is published in https://gitee.com/binzhangbinzhangbin/code-a-novel-attention-based-network-for-fast-salient-object-detection.git
Cooperation between agents in a multi-agent system (MAS) has become a hot topic in recent years, and many algorithms based on centralized training with decentralized execution (CTDE), such as VDN and QMIX, have been proposed. However, these methods disregard the information hidden in the individual action values. In this paper, we propose HyperGraph CoNvolution MIX (HGCN-MIX), a method that combines hypergraph convolution with value decomposition. By treating action values as signals, HGCN-MIX aims to explore the relationship between these signals via a self-learning hypergraph. Experimental results present that HGCN-MIX matches or surpasses state-of-the-art techniques in the StarCraft II multi-agent challenge (SMAC) benchmark on various situations, notably those with a number of agents.
Automatic packing of objects is a critical component for efficient shipping in the Industry 4.0 era. Although robots have shown great success in pick-and-place operations with rigid products, the autonomous shaping and packing of elastic materials into compact boxes remains one of the most challenging problems in robotics; The automation of packing tasks is crucial at this moment given the accelerating shift towards e-commerce (which requires to manipulate multiple types of materials). In this paper, we propose a new action planning approach to automatically pack long linear elastic objects into common-size boxes with a bimanual robotic system. For that, we developed an efficient vision-based method to compute the objects' geometry and track its deformation in real-time and without special markers; The algorithm filters and orders the feedback point cloud that is captured by a depth sensor. A reference object model is introduced to plan the manipulation targets and to complete occluded parts of the object. Action primitives are used to construct high-level behaviors, which enable the execution of all packing steps. To validate the proposed theory, we conduct a detailed experimental study with multiple types and lengths of objects and packing boxes. The proposed methodology is original and its demonstrated manipulation capabilities have not (to the best of the authors knowledge) been previously reported in the literature.
Multi-agent reinforcement learning often suffers from the exponentially larger action space caused by a large number of agents. In this paper, we propose a novel value decomposition framework HAVEN based on hierarchical reinforcement learning for the fully cooperative multi-agent problems. In order to address instabilities that arise from the concurrent optimization of high-level and low-level policies and another concurrent optimization of agents, we introduce the dual coordination mechanism of inter-layer strategies and inter-agent strategies. HAVEN does not require domain knowledge and pretraining at all, and can be applied to any value decomposition variants. Our method is demonstrated to achieve superior results to many baselines on StarCraft II micromanagement tasks and offers an efficient solution to multi-agent hierarchical reinforcement learning in fully cooperative scenarios.