Related papers: Conformal Off-Policy Prediction for Multi-Agent Sy…
Changepoint localization is the problem of estimating the index at which a change occurred in the data generating distribution of an ordered list of data, or declaring that no change occurred. We present the broadly applicable MCP…
*Relative overgeneralization* (RO) occurs in cooperative multi-agent learning tasks when agents converge towards a suboptimal joint policy due to overfitting to suboptimal behavior of other agents. No methods have been proposed for…
Conformal prediction (CP) has emerged as a powerful tool in robotics and control, thanks to its ability to calibrate complex, data-driven models with formal guarantees. However, in robot navigation tasks, existing CP-based methods often…
Decision-making for automated driving remains a challenging task. For their integration into real platforms, these algorithms must guarantee passenger safety and comfort while ensuring interpretability and an appropriate computational time.…
Multi-agent navigation in dynamic environments is of great industrial value when deploying a large scale fleet of robot to real-world applications. This paper proposes a decentralized partially observable multi-agent path planning with…
Contextual bandit algorithms are ubiquitous tools for active sequential experimentation in healthcare and the tech industry. They involve online learning algorithms that adaptively learn policies over time to map observed contexts $X_t$ to…
This work studies the problem of batch off-policy evaluation for Reinforcement Learning in partially observable environments. Off-policy evaluation under partial observability is inherently prone to bias, with risk of arbitrarily large…
Assessing the effects of a policy based on observational data from a different policy is a common problem across several high-stake decision-making domains, and several off-policy evaluation (OPE) techniques have been proposed. However,…
In this paper we analyze the computational power of variants of population protocols (PP), a formalism for distributed systems with anonymous agents having very limited capabilities. The capabilities of agents are enhanced in mediated…
Modern artificial intelligence systems require calibrated uncertainty estimates that remain reliable in sequential and non-stationary environments. Online conformal prediction (OCP) addresses this challenge through adaptively updated…
Spatial public goods games model collective dilemmas where individual payoffs depend on population-level strategy configurations. Most existing studies rely on evolutionary update rules or value-based reinforcement learning methods. These…
This paper studies optimal consensus tracking problem of heterogeneous linear multi-agent systems. By introducing tracking error dynamics, the optimal tracking problem is reformulated as finding a Nash-equilibrium solution of a multi-player…
Comprehensively understanding and accurately predicting the performance of large language models across diverse downstream tasks has emerged as a pivotal challenge in NLP research. The pioneering scaling law on downstream works demonstrated…
In many multiagent scenarios, agents distribute resources, such as time or energy, among several tasks. Having completed their tasks and generated profits, task payoffs must be divided among the agents in some reasonable manner. Cooperative…
Recent advances in Large Language Models (LLMs) have spurred interest in designing LLM-based agents for tasks that involve interaction with human and artificial agents. This paper addresses a key aspect in the design of such agents:…
In dynamic mechanism design literature, one critical aspect has been typically ignored-the agents' periodic participation, which they can adapt and plan strategically. We propose a framework for dynamic principal-multiagent problems,…
Typically, machine learning models are trained and evaluated without making any distinction between users (e.g, using traditional hold-out and cross-validation). However, this produces inaccurate performance metrics estimates in multi-user…
The standard problem setting in Dec-POMDPs is self-play, where the goal is to find a set of policies that play optimally together. Policies learned through self-play may adopt arbitrary conventions and implicitly rely on multi-step…
We present SODA-MPC, a Safe, Out-of-Distribution-Adaptive Model Predictive Control algorithm, which uses an ensemble of learned models for prediction, with a runtime monitor to flag unreliable out-of-distribution (OOD) predictions. When an…
Multi-Agent Path Finding (MAPF) is a fundamental coordination problem in large-scale robotic and cyber-physical systems, where multiple agents must compute conflict-free trajectories with limited computational and communication resources.…