35 citations · 140 across the 26 of their papers we have counts for
32 papers
Asking Smarter Questions: Targeted Active Preference Learning for Underspecified Rewards
Helena Merker, Nick Walker, Andreea Bobu
Reward learning typically assumes the human's input covers everything that matters for the task. In practice, humans can only attend to so much at once, so their teaching naturally…
Language as a Sensor: Calibrated Spatial Belief Estimation in 3D Scenes from Natural Language
Aryan Naveen, Jason Xinyu Liu, Luca Carlone +1
Robots deployed in human-centric environments routinely receive natural-language descriptions of spatial information ("I left my backpack on the table") that reference parts of the…
Human-Guided Harm Recovery for Computer Use Agents
Christy Li, Sky CH-Wang, Andi Peng +1
As LM agents gain the ability to execute actions on real computer systems, we need ways to not only prevent harmful actions at scale but also effectively remediate harm when preven…
Robots That Know What to Ask: Recovering Misaligned Rewards through Targeted Explanations
Helena Merker, Nick Walker, Andreea Bobu
Learning reward functions from demonstrations assumes that demonstrations provide adequate supervision over all features -- or task-relevant aspects of behavior. In practice, demon…
GIFT: Generalizing Intent for Flexible Test-Time Rewards
Fin Amin, Nathaniel Dennler, Andreea Bobu
Robots learn reward functions from user demonstrations, but these rewards often fail to generalize to new environments. This failure occurs because learned rewards latch onto spuri…
Improving through Interaction: Searching Behavioral Representation Spaces with CMA-ES-IG
Nathaniel Dennler, Zhonghao Shi, Yiran Tao +3
Robots that interact with humans must adapt to individual users' preferences to operate effectively in human-centered environments. An intuitive and effective technique to learn no…
Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons
Anthony Liang, Yigit Korkmaz, Jiahui Zhang +14
General-purpose robot reward models are typically trained to predict absolute task progress from expert demonstrations, providing only local, frame-level supervision. While effecti…
Value of Information: A Framework for Human-Agent Communication
Yijiang River Dong, Tiancheng Hu, Zheng Hui +4
Large Language Model (LLM) agents deployed for real-world tasks face a fundamental dilemma: user requests are underspecified, yet agents must decide whether to act on incomplete in…
QuickLAP: Quick Language-Action Preference Learning for Semi-Autonomous Agents
Jordan Abi Nader, David Lee, Nathaniel Dennler +1
Robots must learn from both what people do and what they say, but either modality alone is often incomplete: physical corrections are grounded but ambiguous in intent, while langua…
Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language
Minyoung Hwang, Alexandra Forsey-Smerek, Nathaniel Dennler +1
Robots can adapt to user preferences by learning reward functions from demonstrations, but with limited data, reward models often overfit to spurious correlations and fail to gener…
Flexible Agent Alignment with Goal Inference from Open-Ended Dialog
Rachel Ma, Jingyi Qu, Andreea Bobu +1
We introduce Open-Universe Assistance Games (OU-AGs), a formal framework extending assistance games to LLM-based agents. Effective assistance requires reasoning over human preferen…
Learning Contextually-Adaptive Rewards via Calibrated Features
Alexandra Forsey-Smerek, Julie Shah, Andreea Bobu
A key challenge in reward learning from human input is that desired agent behavior often changes based on context. For example, a robot must adapt to avoid a stove once it becomes…
Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
Mehul Damani, Idan Shenfeld, Andi Peng +2
Computationally intensive decoding procedures--including search, reranking, and self-critique--can improve the quality of language model (LM) outputs in problems spanning code gene…
Goal Inference from Open-Ended Dialog
Rachel Ma, Jingyi Qu, Andreea Bobu +1
Embodied AI Agents are quickly becoming important and common tools in society. These embodied agents should be able to learn about and accomplish a wide range of user goals and pre…
Adaptive Language-Guided Abstraction from Contrastive Explanations
Andi Peng, Belinda Z. Li, Ilia Sucholutsky +4
Many approaches to robot learning begin by inferring a reward function from a set of human demonstrations. To learn a good reward, it is necessary to determine which features of th…
Preference-Conditioned Language-Guided Abstraction
Andi Peng, Andreea Bobu, Belinda Z. Li +5
Learning from demonstrations is a common way for users to teach robots, but it is prone to spurious feature correlations. Recent work constructs state abstractions, i.e. visual rep…
Getting aligned on representational alignment
Ilia Sucholutsky, Lukas Muttenthaler, Adrian Weller +30
Biological and artificial information processing systems form representations of the world that they can use to categorize, reason, plan, navigate, and make decisions. How can we m…
Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation
Andi Peng, Aviv Netanyahu, Mark Ho +4
Policies often fail due to distribution shift -- changes in the state and reward that occur when a policy is deployed in new environments. Data augmentation can increase robustness…
Diagnosing and Augmenting Feature Representations in Correctional Inverse Reinforcement Learning
Inês Lourenço, Andreea Bobu, Cristian R. Rojas +1
Robots have been increasingly better at doing tasks for humans by learning from their feedback, but still often suffer from model misalignment due to missing or incorrectly learned…
Aligning Robot and Human Representations
Andreea Bobu, Andi Peng, Pulkit Agrawal +2
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…
SIRL: Similarity-based Implicit Representation Learning
Andreea Bobu, Yi Liu, Rohin Shah +2
When robots learn reward functions using high capacity models that take raw state directly as input, they need to both learn a representation for what matters in the task -- the ta…
Time-Efficient Reward Learning via Visually Assisted Cluster Ranking
David Zhang, Micah Carroll, Andreea Bobu +1
One of the most successful paradigms for reward learning uses human feedback in the form of comparisons. Although these methods hold promise, human comparison labeling is expensive…
Aligning Robot Representations with Humans
Andreea Bobu, Andi Peng
As robots are increasingly deployed in real-world scenarios, a key question is how to best transfer knowledge learned in one environment to another, where shifting constraints and…
Teaching Robots to Span the Space of Functional Expressive Motion
Arjun Sripathy, Andreea Bobu, Zhongyu Li +3
Our goal is to enable robots to perform functional tasks in emotive ways, be it in response to their users' emotional states, or expressive of their confidence levels. Prior work h…