10 papers
Conformal Constraint Tightening for Chance-Constrained Motion Planning with Unknown Dynamics
Shubham Natraj, Bruno Sinopoli, Yiannis Kantaros
Motion planning algorithms compute control sequences that drive autonomous robots to goal regions while avoiding unsafe states. Existing methods, from sampling-based planning to de…
Deadlock-Free Hybrid RL-MAPF Framework for Zero-Shot Multi-Robot Navigation
Haoyi Wang, Licheng Luo, Yiannis Kantaros +2
Multi-robot navigation in cluttered environments presents fundamental challenges in balancing reactive collision avoidance with long-range goal achievement. When navigating through…
Switched Linear Ensemble Systems and Structural Controllability
Haoyu Yin, Yi Li, Ouyang Du +2
This paper introduces and solves a structural controllability problem for ensembles of switched linear systems. All individual systems in the ensemble are sparse and governed by th…
Conformalized Non-uniform Sampling Strategies for Accelerated Sampling-based Motion Planning
Shubham Natraj, Bruno Sinopoli, Yiannis Kantaros
Sampling-based motion planners (SBMPs) are widely used to compute dynamically feasible robot paths. However, their reliance on uniform sampling often leads to poor efficiency and s…
A Control Theory inspired Exploration Method for a Linear Bandit driven by a Linear Gaussian Dynamical System
Jonathan Gornet, Yilin Mo, Bruno Sinopoli
The paper introduces a linear bandit environment where the reward is the output of a known Linear Gaussian Dynamical System (LGDS). In this environment, we address the fundamental…
On Zero-sum Game Representation for Replicator Dynamics
Haoyu Yin, Xudong Chen, Bruno Sinopoli
Replicator dynamics have been widely used in evolutionary game theory to model how strategy frequencies evolve over time in large populations. The so-called payoff matrix encodes t…
HyperController: A Hyperparameter Controller for Fast and Stable Training of Reinforcement Learning Neural Networks
Jonathan Gornet, Yiannis Kantaros, Bruno Sinopoli
We introduce Hyperparameter Controller (HyperController), a computationally efficient algorithm for hyperparameter optimization during training of reinforcement learning neural net…
An Exploration-free Method for a Linear Stochastic Bandit Driven by a Linear Gaussian Dynamical System
Jonathan Gornet, Yilin Mo, Bruno Sinopoli
In stochastic multi-armed bandits, a major problem the learner faces is the trade-off between exploration and exploitation. Recently, exploration-free methods -- methods that commi…
An Adaptive Method for Contextual Stochastic Multi-armed Bandits with Rewards Generated by a Linear Dynamical System
Jonathan Gornet, Mehdi Hosseinzadeh, Bruno Sinopoli
Online decision-making can be formulated as the popular stochastic multi-armed bandit problem where a learner makes decisions (or takes actions) to maximize cumulative rewards coll…
Restless Bandit Problem with Rewards Generated by a Linear Gaussian Dynamical System
Jonathan Gornet, Bruno Sinopoli
Decision-making under uncertainty is a fundamental problem encountered frequently and can be formulated as a stochastic multi-armed bandit problem. In the problem, the learner inte…