In this paper, a novel optimal control-based baseline function is presented for the policy gradient method in deep reinforcement learning (RL). The baseline is obtained by computing the value function of an optimal control problem, which is formed to be closely associated with the RL task. In contrast to the traditional baseline aimed at variance reduction of policy gradient estimates, our work utilizes the optimal control value function to introduce a novel aspect to the role of baseline -- providing guided exploration during policy learning. This aspect is less discussed in prior works. We validate our baseline on robot learning tasks, showing its effectiveness in guided exploration, particularly in sparse reward environments.
相關內容
This study presents a novel approach for intelligent user interaction interface generation and optimization, grounded in the variational autoencoder (VAE) model. With the rapid advancement of intelligent technologies, traditional interface design methods struggle to meet the evolving demands for diversity and personalization, often lacking flexibility in real-time adjustments to enhance the user experience. Human-Computer Interaction (HCI) plays a critical role in addressing these challenges by focusing on creating interfaces that are functional, intuitive, and responsive to user needs. This research leverages the RICO dataset to train the VAE model, enabling the simulation and creation of user interfaces that align with user aesthetics and interaction habits. By integrating real-time user behavior data, the system dynamically refines and optimizes the interface, improving usability and underscoring the importance of HCI in achieving a seamless user experience. Experimental findings indicate that the VAE-based approach significantly enhances the quality and precision of interface generation compared to other methods, including autoencoders (AE), generative adversarial networks (GAN), conditional GANs (cGAN), deep belief networks (DBN), and VAE-GAN. This work contributes valuable insights into HCI, providing robust technical solutions for automated interface generation and enhanced user experience optimization.
Object detection is a critical task in computer vision, with applications in various domains such as autonomous driving and urban scene monitoring. However, deep learning-based approaches often demand large volumes of annotated data, which are costly and difficult to acquire, particularly in complex and unpredictable real-world environments. This dependency significantly hampers the generalization capability of existing object detection techniques. To address this issue, we introduce a novel single-domain object detection generalization method, named GoDiff, which leverages a pre-trained model to enhance generalization in unseen domains. Central to our approach is the Pseudo Target Data Generation (PTDG) module, which employs a latent diffusion model to generate pseudo-target domain data that preserves source domain characteristics while introducing stylistic variations. By integrating this pseudo data with source domain data, we diversify the training dataset. Furthermore, we introduce a cross-style instance normalization technique to blend style features from different domains generated by the PTDG module, thereby increasing the detector's robustness. Experimental results demonstrate that our method not only enhances the generalization ability of existing detectors but also functions as a plug-and-play enhancement for other single-domain generalization methods, achieving state-of-the-art performance in autonomous driving scenarios.
We study linear contracts for combinatorial problems in multi-agent settings. In this problem, a principal designs a linear contract with several agents, each of whom can decide to take a costly action or not. The principal observes only the outcome of the agents' collective actions, not the actions themselves, and obtains a reward from this outcome. Agents that take an action incur a cost, and so naturally agents require a fraction of the principal's reward as an incentive for taking their action. The principal needs to decide what fraction of their reward to give to each agent so that the principal's expected utility is maximized. Our focus is on the case when the agents are vertices in a graph and the principal's reward corresponds to the number of edges between agents who take their costly action. This case represents the natural scenario when an action of each agent complements actions of other agents though collaborations. Recently, Deo-Campo Vuong et.al. showed that for this problem it is impossible to provide any finite multiplicative approximation or additive FPTAS unless $\mathcal{P} = \mathcal{NP}$. On a positive note, the authors provided an additive PTAS for the case when all agents have the same cost. They asked whether an additive PTAS can be obtained for the general case, i.e when agents potentially have different costs. We answer this open question in positive.
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 aims to recover a multi-subspace matrix from permuted data: given a matrix, in which the columns are drawn from a union of low-dimensional subspaces and some columns are corrupted by permutations on their entries, recover the original matrix. The task has numerous practical applications such as data cleaning, integration, and de-anonymization, but it remains challenging and cannot be well addressed by existing techniques such as robust principal component analysis because of the presence of multiple subspaces and the permutations on the elements of vectors. To solve the challenge, we develop a novel four-stage algorithm pipeline including outlier identification, subspace reconstruction, outlier classification, and unsupervised sensing for permuted vector recovery. Particularly, we provide theoretical guarantees for the outlier classification step, ensuring reliable multi-subspace matrix recovery. Our pipeline is compared with state-of-the-art competitors on multiple benchmarks and shows superior performance.
Quadratic programming (QP) forms a crucial foundation in optimization, encompassing a broad spectrum of domains and serving as the basis for more advanced algorithms. Consequently, as the scale and complexity of modern applications continue to grow, the development of efficient and reliable QP algorithms is becoming increasingly vital. In this context, this paper introduces a novel deep learning-aided distributed optimization architecture designed for tackling large-scale QP problems. First, we combine the state-of-the-art Operator Splitting QP (OSQP) method with a consensus approach to derive DistributedQP, a new method tailored for network-structured problems, with convergence guarantees to optimality. Subsequently, we unfold this optimizer into a deep learning framework, leading to DeepDistributedQP, which leverages learned policies to accelerate reaching to desired accuracy within a restricted amount of iterations. Our approach is also theoretically grounded through Probably Approximately Correct (PAC)-Bayes theory, providing generalization bounds on the expected optimality gap for unseen problems. The proposed framework, as well as its centralized version DeepQP, significantly outperform their standard optimization counterparts on a variety of tasks such as randomly generated problems, optimal control, linear regression, transportation networks and others. Notably, DeepDistributedQP demonstrates strong generalization by training on small problems and scaling to solve much larger ones (up to 50K variables and 150K constraints) using the same policy. Moreover, it achieves orders-of-magnitude improvements in wall-clock time compared to OSQP. The certifiable performance guarantees of our approach are also demonstrated, ensuring higher-quality solutions over traditional optimizers.
Advances in artificial intelligence often stem from the development of new environments that abstract real-world situations into a form where research can be done conveniently. This paper contributes such an environment based on ideas inspired by elementary Microeconomics. Agents learn to produce resources in a spatially complex world, trade them with one another, and consume those that they prefer. We show that the emergent production, consumption, and pricing behaviors respond to environmental conditions in the directions predicted by supply and demand shifts in Microeconomics. We also demonstrate settings where the agents' emergent prices for goods vary over space, reflecting the local abundance of goods. After the price disparities emerge, some agents then discover a niche of transporting goods between regions with different prevailing prices -- a profitable strategy because they can buy goods where they are cheap and sell them where they are expensive. Finally, in a series of ablation experiments, we investigate how choices in the environmental rewards, bartering actions, agent architecture, and ability to consume tradable goods can either aid or inhibit the emergence of this economic behavior. This work is part of the environment development branch of a research program that aims to build human-like artificial general intelligence through multi-agent interactions in simulated societies. By exploring which environment features are needed for the basic phenomena of elementary microeconomics to emerge automatically from learning, we arrive at an environment that differs from those studied in prior multi-agent reinforcement learning work along several dimensions. For example, the model incorporates heterogeneous tastes and physical abilities, and agents negotiate with one another as a grounded form of communication.
We describe ACE0, a lightweight platform for evaluating the suitability and viability of AI methods for behaviour discovery in multiagent simulations. Specifically, ACE0 was designed to explore AI methods for multi-agent simulations used in operations research studies related to new technologies such as autonomous aircraft. Simulation environments used in production are often high-fidelity, complex, require significant domain knowledge and as a result have high R&D costs. Minimal and lightweight simulation environments can help researchers and engineers evaluate the viability of new AI technologies for behaviour discovery in a more agile and potentially cost effective manner. In this paper we describe the motivation for the development of ACE0.We provide a technical overview of the system architecture, describe a case study of behaviour discovery in the aerospace domain, and provide a qualitative evaluation of the system. The evaluation includes a brief description of collaborative research projects with academic partners, exploring different AI behaviour discovery methods.
Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across machine learning disciplines. While it is useful for increasing the generalization capabilities of a model, it can also address many other challenges and problems, from overcoming a limited amount of training data over regularizing the objective to limiting the amount data used to protect privacy. Based on a precise description of the goals and applications of data augmentation (C1) and a taxonomy for existing works (C2), this survey is concerned with data augmentation methods for textual classification and aims to achieve a concise and comprehensive overview for researchers and practitioners (C3). Derived from the taxonomy, we divided more than 100 methods into 12 different groupings and provide state-of-the-art references expounding which methods are highly promising (C4). Finally, research perspectives that may constitute a building block for future work are given (C5).
Federated Learning (FL) is a decentralized machine-learning paradigm, in which a global server iteratively averages the model parameters of local users without accessing their data. User heterogeneity has imposed significant challenges to FL, which can incur drifted global models that are slow to converge. Knowledge Distillation has recently emerged to tackle this issue, by refining the server model using aggregated knowledge from heterogeneous users, other than directly averaging their model parameters. This approach, however, depends on a proxy dataset, making it impractical unless such a prerequisite is satisfied. Moreover, the ensemble knowledge is not fully utilized to guide local model learning, which may in turn affect the quality of the aggregated model. Inspired by the prior art, we propose a data-free knowledge distillation} approach to address heterogeneous FL, where the server learns a lightweight generator to ensemble user information in a data-free manner, which is then broadcasted to users, regulating local training using the learned knowledge as an inductive bias. Empirical studies powered by theoretical implications show that, our approach facilitates FL with better generalization performance using fewer communication rounds, compared with 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