Related papers: Model Proficiency in Centralized Multi-Agent Syste…
One of the major problems in Machine Learning (ML) and Artificial Intelligence (AI) is the fact that the probability distribution of the test data in the real world could deviate substantially from the probability distribution of the…
Sampling-based model predictive control (MPC) has the potential for use in a wide variety of robotic systems. However, its unstable updates and poor convergence render it unsuitable for real-time control of robotic systems. This study…
Selecting an appropriate divergence measure is a critical aspect of machine learning, as it directly impacts model performance. Among the most widely used, we find the Kullback-Leibler (KL) divergence, originally introduced in kinetic…
Multi-agent Reinforcement Learning (MARL) problems often require cooperation among agents in order to solve a task. Centralization and decentralization are two approaches used for cooperation in MARL. While fully decentralized methods are…
This paper presents a learning framework to estimate an agent capability and task requirement model for multi-agent task allocation. With a set of team configurations and the corresponding task performances as the training data, linear task…
We explore the impact of environmental conditions on the competency of machine learning agents and how real-time competency assessments improve the reliability of ML agents. We learn a representation of conditions which impact the…
We study a worst-case approach to measure the sensitivity to model misspecification in the performance analysis of stochastic systems. The situation of interest is when only minimal parametric information is available on the form of the…
We propose a distributed model predictive control (MPC) framework for coordinating heterogeneous, nonlinear multi-agent systems under individual and coupling constraints. The cooperative task is encoded as a shared objective function…
Existing multi-agent perception systems assume that every agent utilizes the same model with identical parameters and architecture. The performance can be degraded with different perception models due to the mismatch in their confidence…
As AI agents powered by large language models (LLMs) increasingly use external tools for high-stakes decisions, a critical reliability question arises: how do errors propagate across sequential tool calls? We introduce the first theoretical…
Agents in dynamic multi-agent environments must monitor their peers to execute individual and group plans. A key open question is how much monitoring of other agents' states is required to be effective: The Monitoring Selectivity Problem.…
Empirical risk minimization, a cornerstone in machine learning, is often hindered by the Optimizer's Curse stemming from discrepancies between the empirical and true data-generating distributions.To address this challenge, the robust…
High-dimensional, heterogeneous data with complex feature interactions pose significant challenges for traditional predictive modeling approaches. While Projection to Latent Structures (PLS) remains a popular technique, it struggles to…
Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark of 86 tasks…
In multi-agent reinforcement learning (MARL), independent learning (IL) often shows remarkable performance and easily scales with the number of agents. Yet, using IL can be inefficient and runs the risk of failing to successfully train,…
Centralised training with decentralised execution (CT-DE) serves as the foundation of many leading multi-agent reinforcement learning (MARL) algorithms. Despite its popularity, it suffers from a critical drawback due to its reliance on…
We study multi-agent reinforcement learning (MARL) in a stochastic network of agents. The objective is to find localized policies that maximize the (discounted) global reward. In general, scalability is a challenge in this setting because…
This paper proposes a decentralized controller for large-scale heterogeneous multi-agent systems subject to bounded external disturbances, where agents must satisfy Signal Temporal Logic (STL) specifications requiring cooperation among…
Many evaluation measures are used to evaluate social biases in masked language models (MLMs). However, we find that these previously proposed evaluation measures are lacking robustness in scenarios with limited datasets. This is because…
When ML algorithms are deployed to automate human-related decisions, human agents may learn the underlying decision policies and adapt their behavior. Strategic Classification (SC) has emerged as a framework for studying this interaction…