3 citations · 3 across the 5 of their papers we have counts for
6 papers
The Linear Representation Hypothesis for Vision-Language-Action Models
Minseok Jeong, Hyewon Choi, Hiroyasu Tsukamoto +1
The linear representation hypothesis (LRH) has become a standard lens for measuring and intervening on semantic information through the internal representations of large language m…
Statistical Convergence of Transformer Encoder-Accelerated Robust Reinforcement Learning
Suman Banerjee, Hiroyasu Tsukamoto
Obtaining the optimal action-value function in Markov decision processes is computationally intensive in large state--action spaces. In this study, we present statistically rigorou…
SCoUT: Scalable Communication via Utility-Guided Temporal Grouping in Multi-Agent Reinforcement Learning
Manav Vora, Gokul Puthumanaillam, Hiroyasu Tsukamoto +1
Communication can improve coordination in partially observed multi-agent reinforcement learning (MARL), but learning \emph{when} and \emph{who} to communicate with requires choosin…
Conformal Contraction for Robust Nonlinear Control with Distribution-Free Uncertainty Quantification
Sihang Wei, Melkior Ornik, Hiroyasu Tsukamoto
We present a novel robust control framework for continuous-time, perturbed nonlinear dynamical systems with uncertainty that depends nonlinearly on both the state and control input…
Statistical Guarantees in Data-Driven Nonlinear Control: Conformal Robustness for Stability and Safety
Ting-Wei Hsu, Hiroyasu Tsukamoto
We present a true-dynamics-agnostic, statistically rigorous framework for establishing exponential stability and safety guarantees of closed-loop, data-driven nonlinear control. Ce…
Information-Optimal Multi-Spacecraft Positioning for Interstellar Object Exploration
Arna Bhardwaj, Shishir Bhatta, Hiroyasu Tsukamoto
Interstellar objects (ISOs), astronomical objects not gravitationally bound to the sun, could present valuable opportunities to advance our understanding of the universe's formatio…