Search Results for author:
Found 62 papers, 15 papers with code
Quantifying Assistive Robustness Via the Natural-Adversarial Frontier
We propose that capturing robustness in these interactive settings requires constructing and analyzing the entire natural-adversarial frontier: the Pareto-frontier of human policies that are the best trade-offs between naturalness and low robot performance.
Confronting Reward Model Overoptimization with Constrained RLHF
Large language models are typically aligned with human preferences by optimizing $\textit{reward models}$ (RMs) fitted to human feedback.
Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning
We further evaluate on a simulated Sawyer pushing task with eye gaze control, and the Lunar Lander game with simulated user commands, and find that our method improves over baseline interfaces in these domains as well.
Contextual Reliability: When Different Features Matter in Different Contexts
We formalize a new setting called contextual reliability which accounts for the fact that the "right" features to use may vary depending on the context.
Aligning Robot and Human Representations
To act in the world, robots rely on a representation of salient task aspects: for example, to carry a coffee mug, a robot may consider movement efficiency or mug orientation in its behavior.
Benchmarks and Algorithms for Offline Preference-Based Reward Learning
Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment.
SIRL: Similarity-based Implicit Representation Learning
This, in turn, is what enables the robot to disambiguate between what needs to go into the representation versus what is spurious, as well as what aspects of behavior can be compressed together versus not.
Learning Representations that Enable Generalization in Assistive Tasks
We advocate that generalization to such OOD policies benefits from (1) learning a good latent representation for human policies that test-time humans can accurately be mapped to, and (2) making that representation adaptable with test-time interaction data, instead of relying on it to perfectly capture the space of human policies based on the simulated population only.
The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types
In this work, we advocate that grounding the rationality coefficient in real data for each feedback type, rather than assuming a default value, has a significant positive effect on reward learning.
First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization
How can we train an assistive human-machine interface (e. g., an electromyography-based limb prosthesis) to translate a user's raw command signals into the actions of a robot or computer when there is no prior mapping, we cannot ask the user for supervision in the form of action labels or reward feedback, and we do not have prior knowledge of the tasks the user is trying to accomplish?
Causal Confusion and Reward Misidentification in Preference-Based Reward Learning
While much prior work focuses on causal confusion in reinforcement learning and behavioral cloning, we focus on a systematic study of causal confusion and reward misidentification when learning from preferences.
X2T: Training an X-to-Text Typing Interface with Online Learning from User Feedback
In the typing domain, we leverage backspaces as feedback that the interface did not perform the desired action.
Teaching Robots to Span the Space of Functional Expressive Motion
As a result 1) all user feedback can contribute to learning about every emotion; 2) the robot can generate trajectories for any emotion in the space instead of only a few predefined ones; and 3) the robot can respond emotively to user-generated natural language by mapping it to a target VAD.
ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning
Building assistive interfaces for controlling robots through arbitrary, high-dimensional, noisy inputs (e. g., webcam images of eye gaze) can be challenging, especially when it involves inferring the user's desired action in the absence of a natural 'default' interface.
Inducing Structure in Reward Learning by Learning Features
To get around this issue, recent deep Inverse Reinforcement Learning (IRL) methods learn rewards directly from the raw state but this is challenging because the robot has to implicitly learn the features that are important and how to combine them, simultaneously.
Assisted Robust Reward Design
We contribute an Assisted Reward Design method that speeds up the design process by anticipating and influencing this future evidence: rather than letting the designer eventually encounter failure cases and revise the reward then, the method actively exposes the designer to such environments during the development phase.
Offline Preference-Based Apprenticeship Learning
Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment.
Pragmatic Image Compression for Human-in-the-Loop Decision-Making
Standard lossy image compression algorithms aim to preserve an image's appearance, while minimizing the number of bits needed to transmit it.
Physical Interaction as Communication: Learning Robot Objectives Online from Human Corrections
We recognize that physical human-robot interaction (pHRI) is often intentional -- the human intervenes on purpose because the robot is not doing the task correctly.
Policy Gradient Bayesian Robust Optimization for Imitation Learning
Results suggest that PG-BROIL can produce a family of behaviors ranging from risk-neutral to risk-averse and outperforms state-of-the-art imitation learning algorithms when learning from ambiguous demonstrations by hedging against uncertainty, rather than seeking to uniquely identify the demonstrator's reward function.
Preference learning along multiple criteria: A game-theoretic perspective
Finally, we showcase the practical utility of our framework in a user study on autonomous driving, where we find that the Blackwell winner outperforms the von Neumann winner for the overall preferences.
Optimal Cost Design for Model Predictive Control
We test our approach in an autonomous driving domain where we find costs different from the ground truth that implicitly compensate for replanning, short horizon, incorrect dynamics models, and local minima issues.
Agnostic learning with unknown utilities
This raises an interesting question whether learning is even possible in our setup, given that obtaining a generalizable estimate of utility $u^*$ might not be possible from finitely many samples.
Situational Confidence Assistance for Lifelong Shared Autonomy
Shared autonomy enables robots to infer user intent and assist in accomplishing it.
Dynamically Switching Human Prediction Models for Efficient Planning
As environments involving both robots and humans become increasingly common, so does the need to account for people during planning.
Analyzing Human Models that Adapt Online
This enables us to leverage tools from reachability analysis and optimal control to compute the set of hypotheses the robot could learn in finite time, as well as the worst and best-case time it takes to learn them.
On complementing end-to-end human behavior predictors with planning
High capacity end-to-end approaches for human motion (behavior) prediction have the ability to represent subtle nuances in human behavior, but struggle with robustness to out of distribution inputs and tail events.
Value Alignment Verification
In this paper we formalize and theoretically analyze the problem of efficient value alignment verification: how to efficiently test whether the behavior of another agent is aligned with a human's values.
Assisted Perception: Optimizing Observations to Communicate State
We evaluate ASE in a user study with 12 participants who each perform four tasks: two tasks with known user biases -- bandwidth-limited image classification and a driving video game with observation delay -- and two with unknown biases that our method has to learn -- guided 2D navigation and a lunar lander teleoperation video game.
Feature Expansive Reward Learning: Rethinking Human Input
When the correction cannot be explained by these features, recent work in deep Inverse Reinforcement Learning (IRL) suggests that the robot could ask for task demonstrations and recover a reward defined over the raw state space.
Reward-rational (implicit) choice: A unifying formalism for reward learning
It is often difficult to hand-specify what the correct reward function is for a task, so researchers have instead aimed to learn reward functions from human behavior or feedback.
Quantifying Hypothesis Space Misspecification in Learning from Human-Robot Demonstrations and Physical Corrections
Recent work focuses on how robots can use such input - like demonstrations or corrections - to learn intended objectives.
LESS is More: Rethinking Probabilistic Models of Human Behavior
A common model is the Boltzmann noisily-rational decision model, which assumes people approximately optimize a reward function and choose trajectories in proportion to their exponentiated reward.
Learning Human Objectives by Evaluating Hypothetical Behavior
To address this challenge, we propose an algorithm that safely and interactively learns a model of the user's reward function.
Nonverbal Robot Feedback for Human Teachers
Robots can learn preferences from human demonstrations, but their success depends on how informative these demonstrations are.
A Hamilton-Jacobi Reachability-Based Framework for Predicting and Analyzing Human Motion for Safe Planning
We construct a new continuous-time dynamical system, where the inputs are the observations of human behavior, and the dynamics include how the belief over the model parameters change.
Scaled Autonomy: Enabling Human Operators to Control Robot Fleets
We learn a model of the user's preferences from observations of the user's choices in easy settings with a few robots, and use it in challenging settings with more robots to automatically identify which robot the user would most likely choose to control, if they were able to evaluate the states of all robots at all times.
Efficient Iterative Linear-Quadratic Approximations for Nonlinear Multi-Player General-Sum Differential Games
We benchmark our method in a three-player general-sum simulated example, in which it takes < 0. 75 s to identify a solution and < 50 ms to solve warm-started subproblems in a receding horizon.
Systems and Control Robotics Systems and Control
Bayesian Robustness: A Nonasymptotic Viewpoint
We study the problem of robustly estimating the posterior distribution for the setting where observed data can be contaminated with potentially adversarial outliers.
On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference
But in the era of deep learning, a natural suggestion researchers make is to avoid mathematical models of human behavior that are fraught with specific assumptions, and instead use a purely data-driven approach.
An Extensible Interactive Interface for Agent Design
In deep reinforcement learning, for example, directly specifying a reward as a function of a high-dimensional observation is challenging.
SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards
Theoretically, we show that SQIL can be interpreted as a regularized variant of BC that uses a sparsity prior to encourage long-horizon imitation.
Literal or Pedagogic Human? Analyzing Human Model Misspecification in Objective Learning
In this work, we focus on misspecification: we argue that robots might not know whether people are being pedagogic or literal and that it is important to ask which assumption is safer to make.
Human-AI Learning Performance in Multi-Armed Bandits
People frequently face challenging decision-making problems in which outcomes are uncertain or unknown.
Establishing Appropriate Trust via Critical States
In order to effectively interact with or supervise a robot, humans need to have an accurate mental model of its capabilities and how it acts.
Robotics
Hierarchical Game-Theoretic Planning for Autonomous Vehicles
This mutual dependence, best captured by dynamic game theory, creates a strong coupling between the vehicle's planning and its predictions of other drivers' behavior, and constitutes an open problem with direct implications on the safety and viability of autonomous driving technology.
Learning under Misspecified Objective Spaces
Learning robot objective functions from human input has become increasingly important, but state-of-the-art techniques assume that the human's desired objective lies within the robot's hypothesis space.
What Would pi* Do?: Imitation Learning via Off-Policy Reinforcement Learning
Learning to imitate expert actions given demonstrations containing image observations is a difficult problem in robotic control.
Cost Functions for Robot Motion Style
We focus on autonomously generating robot motion for day to day physical tasks that is expressive of a certain style or emotion.
Robotics
The Social Cost of Strategic Classification
Consequential decision-making typically incentivizes individuals to behave strategically, tailoring their behavior to the specifics of the decision rule.
Courteous Autonomous Cars
Such a courtesy term enables the robot car to be aware of possible irrationality of the human behavior, and plan accordingly.
Model Reconstruction from Model Explanations
We show through theory and experiment that gradient-based explanations of a model quickly reveal the model itself.
An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning
We apply this update to a variety of POMDP solvers and find that it enables us to scale CIRL to non-trivial problems, with larger reward parameter spaces, and larger action spaces for both robot and human.
Simplifying Reward Design through Divide-and-Conquer
Designing a good reward function is essential to robot planning and reinforcement learning, but it can also be challenging and frustrating.
Probabilistically Safe Robot Planning with Confidence-Based Human Predictions
In order to safely operate around humans, robots can employ predictive models of human motion.
Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior
Inferring intent from observed behavior has been studied extensively within the frameworks of Bayesian inverse planning and inverse reinforcement learning.
Generating Plans that Predict Themselves
We introduce $t$-\ACty{}: a measure that quantifies the accuracy and confidence with which human observers can predict the remaining robot plan from the overall task goal and the observed initial $t$ actions in the plan.
Shared Autonomy via Deep Reinforcement Learning
In shared autonomy, user input is combined with semi-autonomous control to achieve a common goal.
Goal Inference Improves Objective and Perceived Performance in Human-Robot Collaboration
The study of human-robot interaction is fundamental to the design and use of robotics in real-world applications.
Learning from Richer Human Guidance: Augmenting Comparison-Based Learning with Feature Queries
We focus on learning the desired objective function for a robot.
Pragmatic-Pedagogic Value Alignment
In robotics, value alignment is key to the design of collaborative robots that can integrate into human workflows, successfully inferring and adapting to their users' objectives as they go.
Enabling Robots to Communicate their Objectives
We show that certain approximate-inference models lead to the robot generating example behaviors that better enable users to anticipate what it will do in novel situations.
