15 citations · 67 across the 41 of their papers we have counts for
50 papers
Curvature-Guided Sparsification for Graphs with Community Structure
Avin Kolahdooz, Jose Jairo Garcia, Sarah Percival
Graph sparsification in large-scale networks often requires balancing structural accuracy and computational efficiency. Curvature-based methods, particularly Ollivier-Ricci curvatu…
RoboFQE: Rollout-Free Evaluation of Visual Robot Policies from Offline Trajectories
Yunfu Deng, Sangwoo Shin, Brahma S. Pavse +1
Evaluating robot policies before deployment typically requires producing new trajectories through real-world execution, simulators, or learned world models. These rollout-based app…
Informationally Decoupled Trajectory Design for Sim-to-Real System Identification
Sangwoo Shin, Ashvin Anilkumar, Ryan Gao +1
Sampling-based system identification estimates physically meaningful parameters by tuning a simulator to reproduce the target system dynamics, providing an interpretable approach t…
Reinforcement Learning from Real-Robot Interaction without High-Quality State Estimates
Ryan Gao, Ashvin Anilkumar, Nicholas Corrado +2
A longstanding goal for robot reinforcement learning (RL) is that robots learn from their own physical experience, as humans and animals do. A key obstacle to learning directly fro…
Grasp2Twist: Learning Bimanual Dexterous Jar Opening by Reinforcement Learning
Mo Xu, Yunfu Deng, Jianuo Wang +2
This paper presents Grasp2Twist, a bimanual dexterous manipulation system that learns to grasp and twist open jar lids using reinforcement learning. Learning this task raises three…
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…
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…
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…
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…
Articulated-Body Dynamics Network: Dynamics-Grounded Prior for Robot Learning
Sangwoo Shin, Kunzhao Ren, Xiaobin Xiong +1
Recent work in reinforcement learning has shown that incorporating structural priors for articulated robots, such as link connectivity, into policy networks improves learning effic…
Efficient and Versatile Quadrupedal Skating: Optimal Co-design via Reinforcement Learning and Bayesian Optimization
Hanwen Wang, Zhenlong Fang, Josiah Hanna +1
In this paper, we present a hardware-control co-design approach that enables efficient and versatile roller skating on quadrupedal robots equipped with passive wheels. Passive-whee…
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…
When Can Model-Free Reinforcement Learning be Enough for Thinking?
Josiah P. Hanna, Nicholas E. Corrado
Recent work on large language models has demonstrated the use of model-free reinforcement learning (RL) to train reasoning-like capabilities. The emergence of "thinking" through mo…
Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation
Hongyi Zhou, Josiah P. Hanna, Jin Zhu +2
This paper studies off-policy evaluation (OPE) in reinforcement learning with a focus on behavior policy estimation for importance sampling. Prior work has shown empirically that e…
Multi-Robot Collaboration through Reinforcement Learning and Abstract Simulation
Adam Labiosa, Josiah P. Hanna
Teams of people coordinate to perform complex tasks by forming abstract mental models of world and agent dynamics. The use of abstract models contrasts with much recent work in rob…
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…
Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer
Adam Labiosa, Zhihan Wang, Siddhant Agarwal +10
Robot decision-making in partially observable, real-time, dynamic, and multi-agent environments remains a difficult and unsolved challenge. Model-free reinforcement learning (RL) i…
Stable Offline Value Function Learning with Bisimulation-based Representations
Brahma S. Pavse, Yudong Chen, Qiaomin Xie +1
In reinforcement learning, offline value function learning is the procedure of using an offline dataset to estimate the expected discounted return from each state when taking actio…
Reinforcement Learning via Auxiliary Task Distillation
Abhinav Narayan Harish, Larry Heck, Josiah P. Hanna +2
We present Reinforcement Learning via Auxiliary Task Distillation (AuxDistill), a new method that enables reinforcement learning (RL) to perform long-horizon robot control problems…
SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP
Subhojyoti Mukherjee, Josiah P. Hanna, Robert Nowak
In this paper, we study safe data collection for the purpose of policy evaluation in tabular Markov decision processes (MDPs). In policy evaluation, we are given a \textit{target}…
Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning
Subhojyoti Mukherjee, Josiah P. Hanna, Qiaomin Xie +1
We study learning to learn for the multi-task structured bandit problem where the goal is to learn a near-optimal algorithm that minimizes cumulative regret. The tasks share a comm…
Adaptive Exploration for Data-Efficient General Value Function Evaluations
Arushi Jain, Josiah P. Hanna, Doina Precup
General Value Functions (GVFs) (Sutton et al., 2011) represent predictive knowledge in reinforcement learning. Each GVF computes the expected return for a given policy, based on a…
An Empirical Study on the Power of Future Prediction in Partially Observable Environments
Jeongyeol Kwon, Liu Yang, Robert Nowak +1
Learning good representations of historical contexts is one of the core challenges of reinforcement learning (RL) in partially observable environments. While self-predictive auxili…
On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling
Nicholas E. Corrado, Josiah P. Hanna
On-policy reinforcement learning (RL) algorithms are typically characterized as algorithms that perform policy updates using i.i.d. trajectories collected by the agent's current po…