arXiv subjects

Afsaneh Doryab

Publications and source records attributed to Afsaneh Doryab.

16 recordsLinked to original sources

arXiv2026

Coordination Matters: Evaluation of Cooperative Multi-Agent Reinforcement Learning

Cooperative multi-agent reinforcement learning (MARL) benchmarks commonly emphasize aggregate outcomes such as return, success rate, or completion time. While essential, these metrics often fail to reveal how agents coordinate, particularly in settings where agents, tasks, and joint assignment choices scale combinatorially. We propose a coordination-aware evaluation perspective that supplements return with process-level diagnostics. We instantiate this perspective using STAT, a controlled commitment-constrained spatial task-allocation testbed that systematically varies agents, tasks, and environment size while holding observation access and task rules fixed. We evaluate six representative value-based MARL methods across varying levels of centralization. Our results show that similar return trends can reflect distinct coordination mechanisms, including differences in redundant assignment, assignment diversity, and task-completion efficiency. We find that in commitment-constrained task allocation, performance under scale is shaped not only by nominal action-space size, but also by assignment pressure, sparse decision opportunities, and redundant choices among interdependent agents. Our findings motivate coordination-aware evaluation as a necessary complement to return-based benchmarking for cooperative MARL.

cs.MA↗

arXiv2026

SAINT: Attention-Based Policies for Discrete Combinatorial Action Spaces

The combinatorial structure of many real-world action spaces leads to exponential growth in the number of possible actions, limiting the effectiveness of conventional reinforcement learning algorithms. Recent approaches for combinatorial action spaces impose factorized or sequential structures over sub-actions, failing to capture complex joint behavior. We introduce the Sub-Action Interaction Network using Transformers (SAINT), a novel policy architecture that represents multi-component actions as unordered sets and models their dependencies via self-attention conditioned on the global state. SAINT is permutation-invariant, sample-efficient, and compatible with standard policy optimization algorithms. In 18 distinct combinatorial environments across three task domains, including environments with $1.35 \times 10^{18}$ possible actions, SAINT consistently outperforms strong baselines.

cs.LG↗

arXiv2026

Improving and Accelerating Offline RL in Large Discrete Action Spaces with Structured Policy Initialization

Reinforcement learning in discrete combinatorial action spaces requires searching over exponentially many joint actions to simultaneously select multiple sub-actions that form coherent combinations. Existing approaches either simplify policy learning by assuming independence across sub-actions, which often yields incoherent or invalid actions, or attempt to learn action structure and control jointly, which is slow and unstable. We introduce Structured Policy Initialization (SPIN), a two-stage framework that first pre-trains an Action Structure Model (ASM) to capture the manifold of valid actions, then freezes this representation and trains lightweight policy heads for control. On challenging discrete DM Control benchmarks, SPIN improves average return by up to 39% over the state of the art while reducing time to convergence by up to 12.8$\times$.

cs.LG↗

arXiv2026

BraVE: Offline Reinforcement Learning for Discrete Combinatorial Action Spaces

Offline reinforcement learning in high-dimensional, discrete action spaces is challenging due to the exponential scaling of the joint action space with the number of sub-actions and the complexity of modeling sub-action dependencies. Existing methods either exhaustively evaluate the action space, making them computationally infeasible, or factorize Q-values, failing to represent joint sub-action effects. We propose Branch Value Estimation (BraVE), a value-based method that uses tree-structured action traversal to evaluate a linear number of joint actions while preserving dependency structure. BraVE outperforms prior offline RL methods by up to $20\times$ in environments with over four million actions.

cs.LG↗

arXiv2025

Towards an Accessible, Noninvasive Micronutrient Status Assessment Method: A Comprehensive Review of Existing Techniques

Nutrients are critical to the functioning of the human body and their imbalance can result in detrimental health concerns. The majority of nutritional literature focuses on macronutrients, often ignoring the more critical nuances of micronutrient balance, which require more precise regulation. Currently, micronutrient status is routinely assessed via complex methods that are arduous for both the patient and the clinician. To address the global burden of micronutrient malnutrition, innovations in assessment must be accessible and noninvasive. In support of this task, this article synthesizes useful background information on micronutrients themselves, reviews the state of biofluid and physiological analyses for their assessment, and presents actionable opportunities to push the field forward. By taking a unique, clinical perspective that is absent from technological research on the topic, we find that the state of the art suffers from limited clinical relevance, a lack of overlap between biofluid and physiological approaches, and highly invasive and inaccessible solutions. Future work has the opportunity to maximize the impact of a novel assessment method by incorporating clinical relevance, the holistic nature of micronutrition, and prioritizing accessible and noninvasive systems.

q-bio.QM↗

arXiv2025

Factorized Deep Q-Network for Cooperative Multi-Agent Reinforcement Learning in Victim Tagging

Mass casualty incidents (MCIs) are a growing concern, characterized by complexity and uncertainty that demand adaptive decision-making strategies. The victim tagging step in the emergency medical response must be completed quickly and is crucial for providing information to guide subsequent time-constrained response actions. In this paper, we present a mathematical formulation of multi-agent victim tagging to minimize the time it takes for responders to tag all victims. Five distributed heuristics are formulated and evaluated with simulation experiments. The heuristics considered are on-the go, practical solutions that represent varying levels of situational uncertainty in the form of global or local communication capabilities, showcasing practical constraints. We further investigate the performance of a multi-agent reinforcement learning (MARL) strategy, factorized deep Q-network (FDQN), to minimize victim tagging time as compared to baseline heuristics. Extensive simulations demonstrate that between the heuristics, methods with local communication are more efficient for adaptive victim tagging, specifically choosing the nearest victim with the option to replan. Analyzing all experiments, we find that our FDQN approach outperforms heuristics in smaller-scale scenarios, while heuristics excel in more complex scenarios. Our experiments contain diverse complexities that explore the upper limits of MARL capabilities for real-world applications and reveal key insights.

cs.MA↗

arXiv2024

Pairwise Spatiotemporal Partial Trajectory Matching for Co-movement Analysis

Spatiotemporal pairwise movement analysis involves identifying shared geographic-based behaviors between individuals within specific time frames. Traditionally, this task relies on sequence modeling and behavior analysis techniques applied to tabular or video-based data, but these methods often lack interpretability and struggle to capture partial matching. In this paper, we propose a novel method for pairwise spatiotemporal partial trajectory matching that transforms tabular spatiotemporal data into interpretable trajectory images based on specified time windows, allowing for partial trajectory analysis. This approach includes localization of trajectories, checking for spatial overlap, and pairwise matching using a Siamese Neural Network. We evaluate our method on a co-walking classification task, demonstrating its effectiveness in a novel co-behavior identification application. Our model surpasses established methods, achieving an F1-score up to 0.73. Additionally, we explore the method's utility for pair routine pattern analysis in real-world scenarios, providing insights into the frequency, timing, and duration of shared behaviors. This approach offers a powerful, interpretable framework for spatiotemporal behavior analysis, with potential applications in social behavior research, urban planning, and healthcare.

cs.CV↗

arXiv2024

Exploring Smartphone-based Spectrophotometry for Nutrient Identification and Quantification

Imbalanced nutrition is a global health issue with significant downstream effects. Current methods of assessing nutrient levels face several limitations, with accessibility being a major concern. In this paper, we take a step towards accessibly measuring nutrient status within the body. We explore the potential of smartphone-based spectrophotometry for identifying and quantifying nutrients in a solution by building and testing two prototype devices. We compared the prototypes and found that the limitations posed by the initial, simpler prototype were well addressed in the more portable and reliable second-generation device. With the second-generation prototype, we created and implemented a semi-automatic signal processing and analysis pipeline for analyzing absorption spectra. We thoroughly evaluated the prototypes by analyzing the effect of four different light sources and three reference spectra strategies. Results demonstrate that an LED bulb light source performed best, and all reference spectra strategies performed similarly. We then compared the second-generation prototype to a benchtop laboratory spectrophotometer to further validate the device. We applied the Beer-Lambert Law to demonstrate that our prototype is able to quantify the amount of vitamin B12 in a solution with an accuracy of up to 91.3%. Our in-depth analyses, discussions, and results demonstrate the potential use of smartphone-based spectrophotometry as an accessible method to identify and quantify nutrients and pave the way for future developments that can apply this approach to the human body.

physics.med-ph↗

arXiv2021

Towards a Computational Framework for Automated Discovery and Modeling of Biological Rhythms from Wearable Data Streams

Modeling biological rhythms helps understand the complex principles behind the physical and psychological abnormalities of human bodies, to plan life schedules, and avoid persisting fatigue and mood and sleep alterations due to the desynchronization of those rhythms. The first step in modeling biological rhythms is to identify their characteristics, such as cyclic periods, phase, and amplitude. However, human rhythms are susceptible to external events, which cause irregular fluctuations in waveforms and affect the characterization of each rhythm. In this paper, we present our exploratory work towards developing a computational framework for automated discovery and modeling of human rhythms. We first identify cyclic periods in time series data using three different methods and test their performance on both synthetic data and real fine-grained biological data. We observe consistent periods are detected by all three methods. We then model inner cycles within each period through identifying change points to observe fluctuations in biological data that may inform the impact of external events on human rhythms. The results provide initial insights into the design of a computational framework for discovering and modeling human rhythms.

q-bio.QM↗

arXiv2021

Detection of Racial Bias from Physiological Responses

Despite the evolution of norms and regulations to mitigate the harm from biases, harmful discrimination linked to an individual's unconscious biases persists. Our goal is to better understand and detect the physiological and behavioral indicators of implicit biases. This paper investigates whether we can reliably detect racial bias from physiological responses, including heart rate, conductive skin response, skin temperature, and micro-body movements. We analyzed data from 46 subjects whose physiological data was collected with Empatica E4 wristband while taking an Implicit Association Test (IAT). Our machine learning and statistical analysis show that implicit bias can be predicted from physiological signals with 76.1% accuracy. Our results also show that the EDA signal associated with skin response has the strongest correlation with racial bias and that there are significant differences between the values of EDA features for biased and unbiased participants.

cs.AI↗

arXiv2021

Understanding health and behavioral trends of successful students through machine learning models

This study analyzes patterns of physical, mental, lifestyle, and personality factors in college students in different periods over the course of a semester and models their relationships with students' academic performance. The data analyzed was collected through smartphones and Fitbit. The use of machine learning models derived from the gathered data was employed to observe the extent of students' behavior associated with their GPA, lifestyle, physical health, mental health, and personality attributes. A mutual agreement method was used in which rather than looking at the accuracy of results, the model parameters and weights of features were used to find common behavioral trends. From the results of the model creation, it was determined that the most significant indicator of academic success defined as a higher GPA, was the places a student spent their time. Lifestyle and personality factors were deemed more significant than mental and physical factors. This study will provide insight into the impact of different factors and the timing of those factors on students' academic performance.

cs.CY↗

arXiv2020

HHAR-net: Hierarchical Human Activity Recognition using Neural Networks

Activity recognition using built-in sensors in smart and wearable devices provides great opportunities to understand and detect human behavior in the wild and gives a more holistic view of individuals' health and well being. Numerous computational methods have been applied to sensor streams to recognize different daily activities. However, most methods are unable to capture different layers of activities concealed in human behavior. Also, the performance of the models starts to decrease with increasing the number of activities. This research aims at building a hierarchical classification with Neural Networks to recognize human activities based on different levels of abstraction. We evaluate our model on the Extrasensory dataset; a dataset collected in the wild and containing data from smartphones and smartwatches. We use a two-level hierarchy with a total of six mutually exclusive labels namely, "lying down", "sitting", "standing in place", "walking", "running", and "bicycling" divided into "stationary" and "non-stationary". The results show that our model can recognize low-level activities (stationary/non-stationary) with 95.8% accuracy and overall accuracy of 92.8% over six labels. This is 3% above our best performing baseline.

eess.SP↗

arXiv2020

Can Smartphone Co-locations Detect Friendship? It Depends How You Model It

We present a study to detect friendship, its strength, and its change from smartphone location data collectedamong members of a fraternity. We extract a rich set of co-location features and build classifiers that detectfriendships and close friendship at 30% above a random baseline. We design cross-validation schema to testour model performance in specific application settings, finding it robust to seeing new dyads and to temporalvariance.

cs.SI↗

arXiv2019

A Robot's Expressive Language Affects Human Strategy and Perceptions in a Competitive Game

As robots are increasingly endowed with social and communicative capabilities, they will interact with humans in more settings, both collaborative and competitive. We explore human-robot relationships in the context of a competitive Stackelberg Security Game. We vary humanoid robot expressive language (in the form of "encouraging" or "discouraging" verbal commentary) and measure the impact on participants' rationality, strategy prioritization, mood, and perceptions of the robot. We learn that a robot opponent that makes discouraging comments causes a human to play a game less rationally and to perceive the robot more negatively. We also contribute a simple open source Natural Language Processing framework for generating expressive sentences, which was used to generate the speech of our autonomous social robot.

cs.HC↗

arXiv2019

Extraction of Behavioral Features from Smartphone and Wearable Data

The rich set of sensors in smartphones and wearable devices provides the possibility to passively collect streams of data in the wild. The raw data streams, however, can rarely be directly used in the modeling pipeline. We provide a generic framework that can process raw data streams and extract useful features related to non-verbal human behavior. This framework can be used by researchers in the field who are interested in processing data from smartphones and Wearable devices.

cs.CY↗

arXiv2018

The Impact of Humanoid Affect Expression on Human Behavior in a Game-Theoretic Setting

With the rapid development of robot and other intelligent and autonomous agents, how a human could be influenced by a robot's expressed mood when making decisions becomes a crucial question in human-robot interaction. In this pilot study, we investigate (1) in what way a robot can express a certain mood to influence a human's decision making behavioral model; (2) how and to what extent the human will be influenced in a game theoretic setting. More specifically, we create an NLP model to generate sentences that adhere to a specific affective expression profile. We use these sentences for a humanoid robot as it plays a Stackelberg security game against a human. We investigate the behavioral model of the human player.

cs.HC↗