collaborators

16 papers

cs.AI2026

When to Plan: Learning to Select Between Reactive Control and Deliberative Planning

Adam Labiosa, Josiah P. Hanna

It has long been recognized that humans have the ability to switch between fast, reactive decision-making and slower, deliberative planning. In this paper, we study the question of…

cs.RO2026

BIFROST: Bridging Invariant Feature Representation for Observation-space Sim2Real Transfer

Yunfu Deng, Josiah P. Hanna

Sim2real transfer for robot policy learning suffers due to mismatch between simulation and reality. Existing methods typically address each gap in isolation through separate adapta…

cs.CR2026

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning

Kyle Domico, Jean-Charles Noirot Ferrand, Ryan Sheatsley +3

Attacks on machine learning models have been extensively studied through stateless optimization. In this paper, we demonstrate how a reinforcement learning (RL) agent can learn a n…

cs.LG2026

Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling

Nicholas E. Corrado, Wenyuan Huang, Josiah P. Hanna

Multi-task reinforcement learning (MTRL) aims to train a single agent to efficiently optimize performance across multiple tasks simultaneously. However, jointly optimizing all task…

cs.LG2026

Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies

Nicholas E. Corrado, Josiah P. Hanna

Independent on-policy policy gradient algorithms are widely used for multi-agent reinforcement learning (MARL) in cooperative and no-conflict games, but they are known to converge…

cs.RO2026

Abstract Sim2Real through Approximate Information States

Yunfu Deng, Yuhao Li, Josiah P. Hanna

In recent years, reinforcement learning (RL) has shown remarkable success in robotics when a fast and accurate simulator is available for a given task. When using RL and simulation…