Daniel S. Brown

research

∙ 09/20/2023

Swarm Mechanics and Swarm Chemistry: A Transdisciplinary Approach for Robot Swarms

This paper for the first time attempts to bridge the knowledge between c...

0 Ricardo Vega, et al. ∙

research

∙ 07/19/2023

Contextual Reliability: When Different Features Matter in Different Contexts

Deep neural networks often fail catastrophically by relying on spurious ...

0 Gaurav Ghosal, et al. ∙

research

∙ 06/22/2023

Can Differentiable Decision Trees Learn Interpretable Reward Functions?

There is an increasing interest in learning reward functions that model ...

0 Akansha Kalra, et al. ∙

research

∙ 04/25/2023

Leveraging Human Feedback to Evolve and Discover Novel Emergent Behaviors in Robot Swarms

Robot swarms often exhibit emergent behaviors that are fascinating to ob...

0 Connor Mattson, et al. ∙

research

∙ 01/11/2023

Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models

Preference-based reinforcement learning (PbRL) can enable robots to lear...

12 YI LIU, et al. ∙

research

∙ 01/03/2023

Benchmarks and Algorithms for Offline Preference-Based Reward Learning

Learning a reward function from human preferences is challenging as it t...

0 Daniel Shin, et al. ∙

research

∙ 01/02/2023

SIRL: Similarity-based Implicit Representation Learning

When robots learn reward functions using high capacity models that take ...

13 Andreea Bobu, et al. ∙

research

∙ 12/05/2022

Learning Representations that Enable Generalization in Assistive Tasks

Recent work in sim2real has successfully enabled robots to act in physic...

0 Jerry Zhi-Yang He, et al. ∙

research

∙ 11/28/2022

Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning

In this paper we examine the problem of determining demonstration suffic...

0 Tu Trinh, et al. ∙

research

∙ 08/23/2022

The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types

When inferring reward functions from human behavior (be it demonstration...

0 Gaurav R. Ghosal, et al. ∙

research

∙ 07/02/2022

Learning Switching Criteria for Sim2Real Transfer of Robotic Fabric Manipulation Policies

Simulation-to-reality transfer has emerged as a popular and highly succe...

0 Satvik Sharma, et al. ∙

research

∙ 03/04/2022

Teaching Robots to Span the Space of Functional Expressive Motion

Our goal is to enable robots to perform functional tasks in emotive ways...

0 Arjun Sripathy, et al. ∙

research

∙ 11/29/2021

LEGS: Learning Efficient Grasp Sets for Exploratory Grasping

Previous work defined Exploratory Grasping, where a robot iteratively gr...

0 Letian Fu, et al. ∙

research

∙ 09/17/2021

ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning

Effective robot learning often requires online human feedback and interv...

7 Ryan Hoque, et al. ∙

research

∙ 07/20/2021

Offline Preference-Based Apprenticeship Learning

We study how an offline dataset of prior (possibly random) experience ca...

0 Daniel Shin, et al. ∙

research

∙ 07/13/2021

Kit-Net: Self-Supervised Learning to Kit Novel 3D Objects into Novel 3D Cavities

In industrial part kitting, 3D objects are inserted into cavities for tr...

4 Shivin Devgon, et al. ∙

research

∙ 06/11/2021

Policy Gradient Bayesian Robust Optimization for Imitation Learning

The difficulty in specifying rewards for many real-world problems has le...

17 Zaynah Javed, et al. ∙

research

∙ 04/23/2021

Optimal Cost Design for Model Predictive Control

Many robotics domains use some form of nonconvex model predictive contro...

0 Avik Jain, et al. ∙

research

∙ 04/14/2021

Situational Confidence Assistance for Lifelong Shared Autonomy

Shared autonomy enables robots to infer user intent and assist in accomp...

0 Matthew Zurek, et al. ∙

research

∙ 03/31/2021

LazyDAgger: Reducing Context Switching in Interactive Imitation Learning

Corrective interventions while a robot is learning to automate a task pr...

6 Ryan Hoque, et al. ∙

research

∙ 03/13/2021

Dynamically Switching Human Prediction Models for Efficient Planning

As environments involving both robots and humans become increasingly com...

0 Arjun Sripathy, et al. ∙

research

∙ 12/02/2020

Value Alignment Verification

As humans interact with autonomous agents to perform increasingly compli...

0 Daniel S. Brown, et al. ∙

research

∙ 11/11/2020

Exploratory Grasping: Asymptotically Optimal Algorithms for Grasping Challenging Polyhedral Objects

There has been significant recent work on data-driven algorithms for lea...

6 Michael Danielczuk, et al. ∙

research

∙ 07/24/2020

Bayesian Robust Optimization for Imitation Learning

One of the main challenges in imitation learning is determining what act...

23 Daniel S. Brown, et al. ∙

research

∙ 02/21/2020

Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences

Bayesian reward learning from demonstrations enables rigorous safety and...

1 Daniel S. Brown, et al. ∙

research

∙ 12/10/2019

Deep Bayesian Reward Learning from Preferences

Bayesian inverse reinforcement learning (IRL) methods are ideal for safe...

0 Daniel S. Brown, et al. ∙

research

∙ 07/09/2019

Ranking-Based Reward Extrapolation without Rankings

The performance of imitation learning is typically upper-bounded by the ...

0 Daniel S. Brown, et al. ∙

research

∙ 04/12/2019

Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations

A critical flaw of existing inverse reinforcement learning (IRL) methods...

0 Daniel S. Brown, et al. ∙

research

∙ 01/08/2019

Risk-Aware Active Inverse Reinforcement Learning

Active learning from demonstration allows a robot to query a human for s...

0 Daniel S. Brown, et al. ∙

research

∙ 05/20/2018

Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications

Inverse reinforcement learning (IRL) infers a reward function from demon...

0 Daniel S. Brown, et al. ∙

research

∙ 07/03/2017

Efficient Probabilistic Performance Bounds for Inverse Reinforcement Learning

In the field of reinforcement learning there has been recent progress to...

0 Daniel S. Brown, et al. ∙

Daniel S. Brown

Featured Co-authors