Publications associées à Processus de décision markovien

Imitation Learning in Discounted Linear MDPs without exploration assumptions

Volkan Cevher, Efstratios Panteleimon Skoulakis, Luca Viano

We present a new algorithm for imitation learning in infinite horizon linear MDPs dubbed ILARL which greatly improves the bound on the number of trajectories that the learner needs to sample from the environment. In particular, we re- move exploration assu ...

2024

Optimal containment control for a class of heterogeneous multi-agent systems with actuator faults

Ju Wu, Tong Wang

This article investigates the optimal containment control problem for a class of heterogeneous multi-agent systems with time-varying actuator faults and unmatched disturbances based on adaptive dynamic programming. Since there exist unknown input signals i ...

WILEY2023

Multi-robot task allocation for safe planning against stochastic hazard dynamics

Maryam Kamgarpour, Orcun Karaca

We address multi-robot safe mission planning in uncertain dynamic environments. This problem arises in several applications including safety-critical exploration, surveillance, and emergency rescue missions. Computation of a multi-robot optimal control pol ...

IEEE2023

Routing and charging game in ride-hailing service with electric vehicles

John Lygeros, Kenan Zhang

This paper studies the routing and charging behaviors of electric vehicles in a competitive ride-hailing market. When the vehicles are idle, they can choose whether to continue cruising to search for passengers, or move a charging station to recharge. The ...

IEEE2023

On a Finite-Size Neuronal Population Equation

Tilo Schwalger, Valentin Marc Schmutz, Eva Löcherbach

Population equations for infinitely large networks of spiking neurons have a long tradition in theoret-ical neuroscience. In this work, we analyze a recent generalization of these equations to populations of finite size, which takes the form of a nonlinear ...

SIAM PUBLICATIONS2023

Model Predictive Control for Multi-Agent Systems under Limited Communication and Time-Varying Network Topology

Danilo Saccani, Melanie Nicole Zeilinger

In control system networks, reconfiguration of the controller when agents are leaving or joining the network is still an open challenge, in particular when operation constraints that depend on each agent's behavior must be met. Drawing our motivation from ...

IEEE2023

Distributionally Robust Linear Quadratic Control

Daniel Kuhn, Bahar Taskesen, Cagil Kocyigit

Linear-Quadratic-Gaussian (LQG) control is a fundamental control paradigm that is studied in various fields such as engineering, computer science, economics, and neuroscience. It involves controlling a system with linear dynamics and imperfect observations ...

2023

Data-enabled Predictive Control for Empty Vehicle Rebalancing

Nikolaos Geroliminis, Giancarlo Ferrari Trecate, Pengbo Zhu

A critical operational challenge in Mobility-on-demand systems is the problem of imbalance between vehicle supply and passenger demand. However, conventional model-based methods require accurate parametric system models with complex nonlinear dynamics that ...

IEEE2023

Information-Driven Gas Distribution Mapping for Autonomous Mobile Robots

Alcherio Martinoli, Chiara Ercolani, Faezeh Rahbar

The ability to sense airborne pollutants with mobile robots provides a valuable asset for domains such as industrial safety and environmental monitoring. Oftentimes, this involves detecting how certain gases are spread out in the environment, commonly refe ...

MDPI2023

Optimal Combination Policies For Adaptive Social Learning

Virginia Bordignon, Ping Hu, Stefan Vlaski

This paper investigates the effect of combination policies on the performance of adaptive social learning in non-stationary environments. By analyzing the relation between the error probability and the underlying graph topology, we prove that in the slow a ...

IEEE2022