Search

We extend the QLBS model by reformulating via considering a large trader whose transactions leave a permanent impact on the evolution of the exchange rate process and therefore affect the price of contingent claims on such processes. Through a hypothetical limit order book we quantify the exchange rate altered by such transactions. We therefore define the quoted exchange rate process, for which we assume the existence of a postulated hedging strategy. Given the quoted exchange rate and postulated hedging strategy, we find an optimal hedging strategy through batch-mode reinforcement learning given the trader alters the course of the exchange rate process. We assume that the trader has its own concept of fair price and we define our problem as finding the hedging strategy with much lower transaction costs yet delivering a price that well converges to the fair price of the trader. We show our contribution results in an optimal hedging strategy with much lower transaction costs and convergence to the fair price is obtained assuming sensible parameters.

Poultry farming plays a pivotal role in addressing human food demand. Robots are emerging as promising tools in poultry farming, with the potential to address sustainability issues while meeting the increasing production needs and demand for animal welfare. This review aims to identify the current advancements, limitations and future directions of development for robotics in poultry farming by examining existing challenges, solutions and innovative research, including robot-animal interactions. We cover the application of robots in different areas, from environmental monitoring to disease control, floor eggs collection and animal welfare. Robots not only demonstrate effective implementation on farms but also hold potential for ethological research on collective and social behaviour, which can in turn drive a better integration in industrial farming, with improved productivity and enhanced animal welfare., Comment: 50 pages

Contemporary large-scale visual language models (VLMs) exhibit strong representation capacities, making them ubiquitous for enhancing image and text understanding tasks. They are often trained in a contrastive manner on a large and diverse corpus of images and corresponding text captions scraped from the internet. Despite this, VLMs often struggle with compositional reasoning tasks which require a fine-grained understanding of the complex interactions of objects and their attributes. This failure can be attributed to two main factors: 1) Contrastive approaches have traditionally focused on mining negative examples from existing datasets. However, the mined negative examples might not be difficult for the model to discriminate from the positive. An alternative to mining would be negative sample generation 2) But existing generative approaches primarily focus on generating hard negative texts associated with a given image. Mining in the other direction, i.e., generating negative image samples associated with a given text has been ignored. To overcome both these limitations, we propose a framework that not only mines in both directions but also generates challenging negative samples in both modalities, i.e., images and texts. Leveraging these generative hard negative samples, we significantly enhance VLMs' performance in tasks involving multimodal compositional reasoning. Our code and dataset are released at https://ugorsahin.github.io/enhancing-multimodal-compositional-reasoning-of-vlm.html., Comment: Accepted to WACV

We observe a large variety of robots in terms of their bodies, sensors, and actuators. Given the commonalities in the skill sets, teaching each skill to each different robot independently is inefficient and not scalable when the large variety in the robotic landscape is considered. If we can learn the correspondences between the sensorimotor spaces of different robots, we can expect a skill that is learned in one robot can be more directly and easily transferred to other robots. In this paper, we propose a method to learn correspondences among two or more robots that may have different morphologies. To be specific, besides robots with similar morphologies with different degrees of freedom, we show that a fixed-based manipulator robot with joint control and a differential drive mobile robot can be addressed within the proposed framework. To set up the correspondence among the robots considered, an initial base task is demonstrated to the robots to achieve the same goal. Then, a common latent representation is learned along with the individual robot policies for achieving the goal. After the initial learning stage, the observation of a new task execution by one robot becomes sufficient to generate a latent space representation pertaining to the other robots to achieve the same task. We verified our system in a set of experiments where the correspondence between robots is learned (1) when the robots need to follow the same paths to achieve the same task, (2) when the robots need to follow different trajectories to achieve the same task, and (3) when complexities of the required sensorimotor trajectories are different for the robots. We also provide a proof-of-the-concept realization of correspondence learning between a real manipulator robot and a simulated mobile robot., Comment: 8 pages, 12 figures, Submitted to IEEE Robotics Automation Letters (RA-L)

In this work, we report on the effectiveness of our efforts to tailor the personality and conversational style of a conversational agent based on GPT-3.5 and GPT-4 through prompts. We use three personality dimensions with two levels each to create eight conversational agents archetypes. Ten conversations were collected per chatbot, of ten exchanges each, generating 1600 exchanges across GPT-3.5 and GPT-4. Using Linguistic Inquiry and Word Count (LIWC) analysis, we compared the eight agents on language elements including clout, authenticity, and emotion. Four language cues were significantly distinguishing in GPT-3.5, while twelve were distinguishing in GPT-4. With thirteen out of a total nineteen cues in LIWC appearing as significantly distinguishing, our results suggest possible novel prompting approaches may be needed to better suit the creation and evaluation of persistent conversational agent personalities or language styles., Comment: 6 pages, 1 table, PGAI CIKM 2023

We consider a finite-state, continuous-time Markov process, represented in the "linear framework" by a directed graph with labelled edges which specifies the infinitesimal generator of the process. If the graph is strongly connected, the process has a unique steady-state probability distribution, $p$, which may not be one of thermodynamic equilibrium. If the label (rate) of any edge (transition) is perturbed, to reach the new steady-state probability distribution $p'$, we find that the Kullback-Leibler (KL) divergence between these distributions is bounded by the change in the thermodynamic affinity, $\Delta A(C)$, of any cycle, $C$, that includes the altered transition, D$_{KL}$$(p'||p) \leq |\Delta A(C)|$, irrespective of the structure of the graph. It follows that, if an equilibrium distribution is shifted away from equilibrium by perturbing a single rate, then the free energy difference between these distributions is similarly bounded $F^{neq}-F^{eq}\leq |\Delta A(C)|$. Our analysis reveals universal, energy-induced bounds on the information-processing capabilities of Markov systems operating arbitrarily far from thermodynamic equilibrium.

Process mining, a technique turning event data into business process insights, has traditionally operated on the assumption that each event corresponds to a singular case or object. However, many real-world processes are intertwined with multiple objects, making them object-centric. This paper focuses on the emerging domain of object-centric process mining, highlighting its potential yet underexplored benefits in actual operational scenarios. Through an in-depth case study of Borusan Cat's after-sales service process, this study emphasizes the capability of object-centric process mining to capture entangled business process details. Utilizing an event log of approximately 65,000 events, our analysis underscores the importance of embracing this paradigm for richer business insights and enhanced operational improvements.

In this paper, we investigate the robustness of stationary mean-field equilibria in the presence of model uncertainties, specifically focusing on infinite-horizon discounted cost functions. To achieve this, we initially establish convergence conditions for value iteration-based algorithms in mean-field games. Subsequently, utilizing these results, we demonstrate that the mean-field equilibrium obtained through this value iteration algorithm remains robust even in the face of system dynamics misspecifications. We then apply these robustness findings to the finite model approximation problem in mean-field games, showing that if the state space quantization is fine enough, the mean-field equilibrium for the finite model closely approximates the nominal one., Comment: 35 Pages

The death toll and monetary damages from landslides continue to rise despite advancements in predictive modeling. The predictive capability of these models is limited as landslide databases used in training and assessing the models often have crucial information missing, such as underlying failure types. Here, we present an approach for identifying failure types based on their movements, e.g., slides and flows by leveraging 3D landslide topology. We observe topological proxies reveal prevalent signatures of mass movement mechanics embedded in the landslide's morphology or shape, such as detecting coupled movement styles within complex landslides. We find identical failure types exhibit similar topological properties, and by using them as predictors, we can identify failure types in historic and event-specific landslide databases (including multi-temporal) from various geomorphological and climatic contexts such as Italy, the US Pacific Northwest region, Denmark, Turkey, and China with 80 to 94 % accuracy. To demonstrate the real-world application of the method, we implement it in two undocumented datasets from China and publicly release the datasets. These new insights can considerably improve the performance of landslide predictive models and impact assessments. Moreover, our work introduces a new paradigm for studying landslide shapes to understand underlying processes through the lens of landslide topology., Comment: 23 pages, 11 figures

In this article, we study the properties of a class of functional spaces which arise from the investigation of nonlinear differential equations. We establish some integral inequalities then by applying these inequalities, we prove some lemmas and theorems, which indicate the relation of these spaces (pn-spaces) with the Lebesgue and Sobolev spaces in the case when pn-spaces with constant and variable exponents.

Inverted pendulums constitute one of the popular systems for benchmarking control algorithms. Several methods have been proposed for the control of this system, the majority of which rely on the availability of a mathematical model. However, deriving a mathematical model using physical parameters or system identification techniques requires manual effort. Moreover, the designed controllers may perform poorly if system parameters change. To mitigate these problems, recently, some studies used Reinforcement Learning (RL) based approaches for the control of inverted pendulum systems. Unfortunately, these methods suffer from slow convergence and local minimum problems. Moreover, they may require hyperparameter tuning which complicates the design process significantly. To alleviate these problems, the present study proposes an LQR-based RL method for adaptive balancing control of an inverted pendulum. As shown by numerical experiments, the algorithm stabilizes the system very fast without requiring a mathematical model or extensive hyperparameter tuning. In addition, it can adapt to parametric changes online.

Machine learning studies need colossal power to process massive datasets and train neural networks to reach high accuracies, which have become gradually unsustainable. Limited by the von Neumann bottleneck, current computing architectures and methods fuel this high power consumption. Here, we present an analog computing method that harnesses chaotic nonlinear attractors to perform machine learning tasks with low power consumption. Inspired by neuromorphic computing, our model is a programmable, versatile, and generalized platform for machine learning tasks. Our mode provides exceptional performance in clustering by utilizing chaotic attractors' nonlinear mapping and sensitivity to initial conditions. When deployed as a simple analog device, it only requires milliwatt-scale power levels while being on par with current machine learning techniques. We demonstrate low errors and high accuracies with our model for regression and classification-based learning tasks., Comment: Manuscript is 13 pages, 4 figures. Supplementary Material is 6 pages, 3 figures

Learning object affordances is an effective tool in the field of robot learning. While the data-driven models investigate affordances of single or paired objects, there is a gap in the exploration of affordances of compound objects composed of an arbitrary number of objects. We propose the Multi-Object Graph Affordance Network which models complex compound object affordances by learning the outcomes of robot actions that facilitate interactions between an object and a compound. Given the depth images of the objects, the object features are extracted via convolution operations and encoded in the nodes of graph neural networks. Graph convolution operations are used to encode the state of the compounds, which are used as input to decoders to predict the outcome of the object-compound interactions. After learning the compound object affordances, given different tasks, the learned outcome predictors are used to plan sequences of stack actions that involve stacking objects on top of each other, inserting smaller objects into larger containers and passing through ring-like objects through poles. We showed that our system successfully modeled the affordances of compound objects that include concave and convex objects, in both simulated and real-world environments. We benchmarked our system with a baseline model to highlight its advantages., Comment: This work has been submitted to the IEEE for possible publication

Intraductal Papillary Mucinous Neoplasm (IPMN) cysts are pre-malignant pancreas lesions, and they can progress into pancreatic cancer. Therefore, detecting and stratifying their risk level is of ultimate importance for effective treatment planning and disease control. However, this is a highly challenging task because of the diverse and irregular shape, texture, and size of the IPMN cysts as well as the pancreas. In this study, we propose a novel computer-aided diagnosis pipeline for IPMN risk classification from multi-contrast MRI scans. Our proposed analysis framework includes an efficient volumetric self-adapting segmentation strategy for pancreas delineation, followed by a newly designed deep learning-based classification scheme with a radiomics-based predictive approach. We test our proposed decision-fusion model in multi-center data sets of 246 multi-contrast MRI scans and obtain superior performance to the state of the art (SOTA) in this field. Our ablation studies demonstrate the significance of both radiomics and deep learning modules for achieving the new SOTA performance compared to international guidelines and published studies (81.9\% vs 61.3\% in accuracy). Our findings have important implications for clinical decision-making. In a series of rigorous experiments on multi-center data sets (246 MRI scans from five centers), we achieved unprecedented performance (81.9\% accuracy)., Comment: 10 pages, MICCAI MLMI 2023

Exploratoration and self-observation are key mechanisms of infant sensorimotor development. These processes are further guided by parental scaffolding accelerating skill and knowledge acquisition. In developmental robotics, this approach has been adopted often by having a human acting as the source of scaffolding. In this study, we investigate whether Large Language Models (LLMs) can act as a scaffolding agent for a robotic system that aims to learn to predict the effects of its actions. To this end, an object manipulation setup is considered where one object can be picked and placed on top of or in the vicinity of another object. The adopted LLM is asked to guide the action selection process through algorithmically generated state descriptions and action selection alternatives in natural language. The simulation experiments that include cubes in this setup show that LLM-guided (GPT3.5-guided) learning yields significantly faster discovery of novel structures compared to random exploration. However, we observed that GPT3.5 fails to effectively guide the robot in generating structures with different affordances such as cubes and spheres. Overall, we conclude that even without fine-tuning, LLMs may serve as a moderate scaffolding agent for improving robot learning, however, they still lack affordance understanding which limits the applicability of the current LLMs in robotic scaffolding tasks., Comment: To appear in IEEE Transactions on Robotics \copyright IEEE2023

In this paper, we propose and realize a new deep learning architecture for discovering symbolic representations for objects and their relations based on the self-supervised continuous interaction of a manipulator robot with multiple objects on a tabletop environment. The key feature of the model is that it can handle a changing number number of objects naturally and map the object-object relations into symbolic domain explicitly. In the model, we employ a self-attention layer that computes discrete attention weights from object features, which are treated as relational symbols between objects. These relational symbols are then used to aggregate the learned object symbols and predict the effects of executed actions on each object. The result is a pipeline that allows the formation of object symbols and relational symbols from a dataset of object features, actions, and effects in an end-to-end manner. We compare the performance of our proposed architecture with state-of-the-art symbol discovery methods in a simulated tabletop environment where the robot needs to discover symbols related to the relative positions of objects to predict the observed effect successfully. Our experiments show that the proposed architecture performs better than other baselines in effect prediction while forming not only object symbols but also relational symbols. Furthermore, we analyze the learned symbols and relational patterns between objects to learn about how the model interprets the environment. Our analysis shows that the learned symbols relate to the relative positions of objects, object types, and their horizontal alignment on the table, which reflect the regularities in the environment., Comment: arXiv admin note: text overlap with arXiv:2208.01021