The ability to learn robust policies while generalizing over large discrete action spaces is an open challenge for intelligent systems, especially in noisy environments that face the curse of dimensionality. In this paper, we present a novel framework to efficiently learn action embeddings that simultaneously allow us to reconstruct the original action as well as to predict the expected future state. We describe an encoder-decoder architecture for action embeddings with a dual channel loss that balances between action reconstruction and state prediction accuracy. We use the trained decoder in conjunction with a standard reinforcement learning algorithm that produces actions in the embedding space. Our architecture is able to outperform two competitive baselines in two diverse environments: a 2D maze environment with more than 4000 discrete noisy actions, and a product recommendation task that uses real-world e-commerce transaction data. Empirical results show that the model results in cleaner action embeddings, and the improved representations help learn better policies with earlier convergence.
相關內容
With the continuous evolution and refinement of LLMs, they are endowed with impressive logical reasoning or vertical thinking capabilities. But can they think out of the box? Do they possess proficient lateral thinking abilities? Following the setup of Lateral Thinking Puzzles, we propose a novel evaluation benchmark, LatEval, which assesses the model's lateral thinking within an interactive framework. In our benchmark, we challenge LLMs with 2 aspects: the quality of questions posed by the model and the model's capability to integrate information for problem-solving. We find that nearly all LLMs struggle with employing lateral thinking during interactions. For example, even the most advanced model, GPT-4, exhibits the advantage to some extent, yet still maintain a noticeable gap when compared to human. This evaluation benchmark provides LLMs with a highly challenging and distinctive task that is crucial to an effective AI assistant.
Psychological trait estimation from external factors such as movement and appearance is a challenging and long-standing problem in psychology, and is principally based on the psychological theory of embodiment. To date, attempts to tackle this problem have utilized private small-scale datasets with intrusive body-attached sensors. Potential applications of an automated system for psychological trait estimation include estimation of occupational fatigue and psychology, and marketing and advertisement. In this work, we propose PsyMo (Psychological traits from Motion), a novel, multi-purpose and multi-modal dataset for exploring psychological cues manifested in walking patterns. We gathered walking sequences from 312 subjects in 7 different walking variations and 6 camera angles. In conjunction with walking sequences, participants filled in 6 psychological questionnaires, totalling 17 psychometric attributes related to personality, self-esteem, fatigue, aggressiveness and mental health. We propose two evaluation protocols for psychological trait estimation. Alongside the estimation of self-reported psychological traits from gait, the dataset can be used as a drop-in replacement to benchmark methods for gait recognition. We anonymize all cues related to the identity of the subjects and publicly release only silhouettes, 2D / 3D human skeletons and 3D SMPL human meshes.
The reconfigurable intelligent surface (RIS) is a promising technology that enables wireless communication systems to achieve improved performance by intelligently manipulating wireless channels. In this paper, we consider the sum-rate maximization problem in a downlink multi-user multi-input-single-output (MISO) channel via space-division multiple access (SDMA). Two major challenges of this problem are the high dimensionality due to the large number of RIS elements and the difficulty to obtain the full channel state information (CSI), which is assumed known in many algorithms proposed in the literature. Instead, we propose a hybrid machine learning approach using the weighted minimum mean squared error (WMMSE) precoder at the base station (BS) and a dedicated neural network (NN) architecture, RISnet, for RIS configuration. The RISnet has a good scalability to optimize 1296 RIS elements and requires partial CSI of only 16 RIS elements as input. We show it achieves a high performance with low requirement for channel estimation for geometric channel models obtained with ray-tracing simulation. The unsupervised learning lets the RISnet find an optimized RIS configuration by itself. Numerical results show that a trained model configures the RIS with low computational effort, considerably outperforms the baselines, and can work with discrete phase shifts.
Although explainable computational creativity seeks to create and sustain computational models of creativity that foster a collaboratively creative process through explainability, there remains little to no work in supporting designers when exploring the explanation medium. While explainable artificial intelligence methods tend to support textual, visual, and numerical explanations, within the arts, interaction mediums such as auditorial, tactile, and olfactoral may offer more salient communication within the creative process itself. Through this research, I propose a framework to assist designers of explainable user interfaces in modeling the type of interaction they wish to create using explanations.
Movable antenna (MA) is an emerging technology which enables a local movement of the antenna in the transmitter/receiver region for improving the channel condition and communication performance. In this paper, we study the deployment of multiple MAs at the base station (BS) for enhancing the multiuser communication performance. First, we model the multiuser channel in the uplink to characterize the wireless channel variation due to MAs' movements at the BS. Then, an optimization problem is formulated to maximize the minimum achievable rate among multiple users for MA-aided uplink multiuser communications by jointly optimizing the MAs' positions, their receive combining at the BS, and the transmit power of users, under the constraints of finite moving region for MAs, minimum inter-MA distance, and maximum transmit power of each user. To solve this challenging non-convex optimization problem, a two-loop iterative algorithm is proposed by leveraging the particle swarm optimization (PSO) method. Specifically, the outer-loop updates the positions of a set of particles, where each particle's position represents one realization of the antenna position vector (APV) of all MAs. The inner-loop implements the fitness evaluation for each particle in terms of the max-min achievable rate of multiple users with its corresponding APV, where the receive combining matrix of the BS and the transmit power of each user are optimized by applying the block coordinate descent (BCD) technique. Simulation results show that the antenna position optimization for MAs-aided BSs can significantly improve the rate performance as compared to conventional BSs with fixed-position antennas (FPAs).
RF fingerprinting is emerging as a physical layer security scheme to identify illegitimate and/or unauthorized emitters sharing the RF spectrum. However, due to the lack of publicly accessible real-world datasets, most research focuses on generating synthetic waveforms with software-defined radios (SDRs) which are not suited for practical deployment settings. On other hand, the limited datasets that are available focus only on chipsets that generate only one kind of waveform. Commercial off-the-shelf (COTS) combo chipsets that support two wireless standards (for example WiFi and Bluetooth) over a shared dual-band antenna such as those found in laptops, adapters, wireless chargers, Raspberry Pis, among others are becoming ubiquitous in the IoT realm. Hence, to keep up with the modern IoT environment, there is a pressing need for real-world open datasets capturing emissions from these combo chipsets transmitting heterogeneous communication protocols. To this end, we capture the first known emissions from the COTS IoT chipsets transmitting WiFi and Bluetooth under two different time frames. The different time frames are essential to rigorously evaluate the generalization capability of the models. To ensure widespread use, each capture within the comprehensive 72 GB dataset is long enough (40 MSamples) to support diverse input tensor lengths and formats. Finally, the dataset also comprises emissions at varying signal powers to account for the feeble to high signal strength emissions as encountered in a real-world setting.
We consider a setting in which one swarm of agents is to service or track a second swarm, and formulate an optimal control problem which trades off between the competing objectives of servicing and motion costs. We consider the continuum limit where large-scale swarms are modeled in terms of their time-varying densities, and where the Wasserstein distance between two densities captures the servicing cost. We show how this non-linear infinite-dimensional optimal control problem is intimately related to the geometry of Wasserstein space, and provide new results in the case of absolutely continuous densities and constant-in-time references. Specifically, we show that optimal swarm trajectories follow Wasserstein geodesics, while the optimal control tradeoff determines the time-schedule of travel along these geodesics. We briefly describe how this solution provides a basis for a model-predictive control scheme for tracking time-varying and real-time reference trajectories as well.
The existence of representative datasets is a prerequisite of many successful artificial intelligence and machine learning models. However, the subsequent application of these models often involves scenarios that are inadequately represented in the data used for training. The reasons for this are manifold and range from time and cost constraints to ethical considerations. As a consequence, the reliable use of these models, especially in safety-critical applications, is a huge challenge. Leveraging additional, already existing sources of knowledge is key to overcome the limitations of purely data-driven approaches, and eventually to increase the generalization capability of these models. Furthermore, predictions that conform with knowledge are crucial for making trustworthy and safe decisions even in underrepresented scenarios. This work provides an overview of existing techniques and methods in the literature that combine data-based models with existing knowledge. The identified approaches are structured according to the categories integration, extraction and conformity. Special attention is given to applications in the field of autonomous driving.
Image segmentation is still an open problem especially when intensities of the interested objects are overlapped due to the presence of intensity inhomogeneity (also known as bias field). To segment images with intensity inhomogeneities, a bias correction embedded level set model is proposed where Inhomogeneities are Estimated by Orthogonal Primary Functions (IEOPF). In the proposed model, the smoothly varying bias is estimated by a linear combination of a given set of orthogonal primary functions. An inhomogeneous intensity clustering energy is then defined and membership functions of the clusters described by the level set function are introduced to rewrite the energy as a data term of the proposed model. Similar to popular level set methods, a regularization term and an arc length term are also included to regularize and smooth the level set function, respectively. The proposed model is then extended to multichannel and multiphase patterns to segment colourful images and images with multiple objects, respectively. It has been extensively tested on both synthetic and real images that are widely used in the literature and public BrainWeb and IBSR datasets. Experimental results and comparison with state-of-the-art methods demonstrate that advantages of the proposed model in terms of bias correction and segmentation accuracy.
Detecting carried objects is one of the requirements for developing systems to reason about activities involving people and objects. We present an approach to detect carried objects from a single video frame with a novel method that incorporates features from multiple scales. Initially, a foreground mask in a video frame is segmented into multi-scale superpixels. Then the human-like regions in the segmented area are identified by matching a set of extracted features from superpixels against learned features in a codebook. A carried object probability map is generated using the complement of the matching probabilities of superpixels to human-like regions and background information. A group of superpixels with high carried object probability and strong edge support is then merged to obtain the shape of the carried object. We applied our method to two challenging datasets, and results show that our method is competitive with or better than the state-of-the-art.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191