In this paper, we seek to learn a robot policy guaranteed to satisfy state constraints. To encourage constraint satisfaction, existing RL algorithms typically rely on Constrained Markov Decision Processes and discourage constraint violations through reward shaping. However, such soft constraints cannot offer verifiable safety guarantees. To address this gap, we propose POLICEd RL, a novel RL algorithm explicitly designed to enforce affine hard constraints in closed-loop with a black-box environment. Our key insight is to force the learned policy to be affine around the unsafe set and use this affine region as a repulsive buffer to prevent trajectories from violating the constraint. We prove that such policies exist and guarantee constraint satisfaction. Our proposed framework is applicable to both systems with continuous and discrete state and action spaces and is agnostic to the choice of the RL training algorithm. Our results demonstrate the capacity of POLICEd RL to enforce hard constraints in robotic tasks while significantly outperforming existing methods.
相關內容
In this paper, we focus on the challenging task of reliably estimating factual knowledge that is embedded inside large language models (LLMs). To avoid reliability concerns with prior approaches, we propose to eliminate prompt engineering when probing LLMs for factual knowledge. Our approach, called Zero-Prompt Latent Knowledge Estimator (ZP-LKE), leverages the in-context learning ability of LLMs to communicate both the factual knowledge question as well as the expected answer format. Our knowledge estimator is both conceptually simpler (i.e., doesn't depend on meta-linguistic judgments of LLMs) and easier to apply (i.e., is not LLM-specific), and we demonstrate that it can surface more of the latent knowledge embedded in LLMs. We also investigate how different design choices affect the performance of ZP-LKE. Using the proposed estimator, we perform a large-scale evaluation of the factual knowledge of a variety of open-source LLMs, like OPT, Pythia, Llama(2), Mistral, Gemma, etc. over a large set of relations and facts from the Wikidata knowledge base. We observe differences in the factual knowledge between different model families and models of different sizes, that some relations are consistently better known than others but that models differ in the precise facts they know, and differences in the knowledge of base models and their finetuned counterparts. Code available at: //github.com/QinyuanWu0710/ZeroPrompt_LKE
This paper proposes a new design method for a stochastic control policy using a normalizing flow (NF). In reinforcement learning (RL), the policy is usually modeled as a distribution model with trainable parameters. When this parameterization has less expressiveness, it would fail to acquiring the optimal policy. A mixture model has capability of a universal approximation, but it with too much redundancy increases the computational cost, which can become a bottleneck when considering the use of real-time robot control. As another approach, NF, which is with additional parameters for invertible transformation from a simple stochastic model as a base, is expected to exert high expressiveness and lower computational cost. However, NF cannot compute its mean analytically due to complexity of the invertible transformation, and it lacks reliability because it retains stochastic behaviors after deployment for robot controller. This paper therefore designs a restricted NF (RNF) that achieves an analytic mean by appropriately restricting the invertible transformation. In addition, the expressiveness impaired by this restriction is regained using bimodal student-t distribution as its base, so-called Bit-RNF. In RL benchmarks, Bit-RNF policy outperformed the previous models. Finally, a real robot experiment demonstrated the applicability of Bit-RNF policy to real world. The attached video is uploaded on youtube: //youtu.be/R_GJVZDW9bk
Noise-Resilient Homomorphic Encryption: A Framework for Secure Data Processing in Health care Domain
In this paper, we introduce the Fully Homomorphic Integrity Model (HIM), a novel approach designed to enhance security, efficiency, and reliability in encrypted data processing, primarily within the health care industry. HIM addresses the key challenges that noise accumulation, computational overheads, and data integrity pose during homomorphic operations. Our contribution of HIM: advances in noise management through the rational number adjustment; key generation based on personalized prime numbers; and time complexity analysis details for key operations. In HIM, some additional mechanisms were introduced, including robust mechanisms of decryption. Indeed, the decryption mechanism ensures that the data recovered upon doing complex homomorphic computation will be valid and reliable. The healthcare id model is tested, and it supports real-time processing of data with privacy maintained concerning patients. It supports analytics and decision-making processes without any compromise on the integrity of information concerning patients. Output HIM promotes the efficiency of encryption to a greater extent as it reduces the encryption time up to 35ms and decryption time up to 140ms, which is better when compared to other models in the existence. Ciphertext size also becomes the smallest one, which is 4KB. Our experiments confirm that HIM is indeed a very efficient and secure privacy-preserving solution for healthcare applications
In this paper we focus on inserting a given human (specifically, a single image of a person) into a novel scene. Our method, which builds on top of Stable Diffusion, yields natural looking images while being highly controllable with text and pose. To accomplish this we need to train on pairs of images, the first a reference image with the person, the second a "target image" showing the same person (with a different pose and possibly in a different background). Additionally we require a text caption describing the new pose relative to that in the reference image. In this paper we present a novel dataset following this criteria, which we create using pairs of frames from human-centric and action-rich videos and employing a multimodal LLM to automatically summarize the difference in human pose for the text captions. We demonstrate that identity preservation is a more challenging task in scenes "in-the-wild", and especially scenes where there is an interaction between persons and objects. Combining the weak supervision from noisy captions, with robust 2D pose improves the quality of person-object interactions.
In human social systems, debates are often seen as a means to resolve differences of opinion. However, in reality, debates frequently incur significant communication costs, especially when dealing with stubborn opponents. Inspired by this phenomenon, this paper examines the impact of malicious agents on the evolution of normal agents' opinions from the perspective of opinion evolution cost, and proposes corresponding solutions for the scenario in which malicious agents hold different opinions in multi-agent systems(MASs). First, this paper analyzes the negative impact of malicious agents on the opinion evolution process, reveals the additional evolution cost it brings, and provides a theoretical basis for the subsequent solutions. Secondly, based on the characteristics of opinion evolution, the malicious agent isolation algorithm based on opinion evolution direction vector is proposed, which does not strongly restrict the proportion of malicious agents. Additionally, an evolution rate adjustment mechanism is introduced, allowing the system to flexibly regulate the evolution process in complex situations, effectively achieving the trade-off between opinion evolution rate and cost. Extensive numerical simulations demonstrate that the algorithm can effectively eliminate the negative influence of malicious agents and achieve a balance between opinion evolution costs and convergence speed.
In this paper, we present a Hoare-style logic for reasoning about quantum programs with classical variables. Our approach offers several improvements over previous work: (1) Enhanced expressivity of the programming language: Our logic applies to quantum programs with classical variables that incorporate quantum arrays and parameterised quantum gates, which have not been addressed in previous research on quantum Hoare logic, either with or without classical variables. (2) Intuitive correctness specifications: In our logic, preconditions and postconditions for quantum programs with classical variables are specified as a pair consisting of a classical first-order logical formula and a quantum predicate formula (possibly parameterised by classical variables). These specifications offer greater clarity and align more closely with the programmer's intuitive understanding of quantum and classical interactions. (3) Simplified proof system: By introducing a novel idea in formulating a proof rule for reasoning about quantum measurements, along with (2), we develop a proof system for quantum programs that requires only minimal modifications to classical Hoare logic. Furthermore, this proof system can be effectively and conveniently combined with classical first-order logic to verify quantum programs with classical variables. As a result, the learning curve for quantum program verification techniques is significantly reduced for those already familiar with classical program verification techniques, and existing tools for verifying classical programs can be more easily adapted for quantum program verification.
In pace with developments in the research field of artificial intelligence, knowledge graphs (KGs) have attracted a surge of interest from both academia and industry. As a representation of semantic relations between entities, KGs have proven to be particularly relevant for natural language processing (NLP), experiencing a rapid spread and wide adoption within recent years. Given the increasing amount of research work in this area, several KG-related approaches have been surveyed in the NLP research community. However, a comprehensive study that categorizes established topics and reviews the maturity of individual research streams remains absent to this day. Contributing to closing this gap, we systematically analyzed 507 papers from the literature on KGs in NLP. Our survey encompasses a multifaceted review of tasks, research types, and contributions. As a result, we present a structured overview of the research landscape, provide a taxonomy of tasks, summarize our findings, and highlight directions for future work.
Link prediction is a very fundamental task on graphs. Inspired by traditional path-based methods, in this paper we propose a general and flexible representation learning framework based on paths for link prediction. Specifically, we define the representation of a pair of nodes as the generalized sum of all path representations, with each path representation as the generalized product of the edge representations in the path. Motivated by the Bellman-Ford algorithm for solving the shortest path problem, we show that the proposed path formulation can be efficiently solved by the generalized Bellman-Ford algorithm. To further improve the capacity of the path formulation, we propose the Neural Bellman-Ford Network (NBFNet), a general graph neural network framework that solves the path formulation with learned operators in the generalized Bellman-Ford algorithm. The NBFNet parameterizes the generalized Bellman-Ford algorithm with 3 neural components, namely INDICATOR, MESSAGE and AGGREGATE functions, which corresponds to the boundary condition, multiplication operator, and summation operator respectively. The NBFNet is very general, covers many traditional path-based methods, and can be applied to both homogeneous graphs and multi-relational graphs (e.g., knowledge graphs) in both transductive and inductive settings. Experiments on both homogeneous graphs and knowledge graphs show that the proposed NBFNet outperforms existing methods by a large margin in both transductive and inductive settings, achieving new state-of-the-art results.
In this paper, we present a comprehensive review of the imbalance problems in object detection. To analyze the problems in a systematic manner, we introduce a problem-based taxonomy. Following this taxonomy, we discuss each problem in depth and present a unifying yet critical perspective on the solutions in the literature. In addition, we identify major open issues regarding the existing imbalance problems as well as imbalance problems that have not been discussed before. Moreover, in order to keep our review up to date, we provide an accompanying webpage which catalogs papers addressing imbalance problems, according to our problem-based taxonomy. Researchers can track newer studies on this webpage available at: //github.com/kemaloksuz/ObjectDetectionImbalance .
Salient object detection is a problem that has been considered in detail and many solutions proposed. In this paper, we argue that work to date has addressed a problem that is relatively ill-posed. Specifically, there is not universal agreement about what constitutes a salient object when multiple observers are queried. This implies that some objects are more likely to be judged salient than others, and implies a relative rank exists on salient objects. The solution presented in this paper solves this more general problem that considers relative rank, and we propose data and metrics suitable to measuring success in a relative objects saliency landscape. A novel deep learning solution is proposed based on a hierarchical representation of relative saliency and stage-wise refinement. We also show that the problem of salient object subitizing can be addressed with the same network, and our approach exceeds performance of any prior work across all metrics considered (both traditional and newly proposed).
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191