21 accepted papers
Generative policies trained with human demonstrations can autonomously accomplish multimodal, longhorizon tasks. However, during inference, humans are often removed from the policy execution loop, limiting the ability to guide a pre-trained policy towards a specific sub-goal or trajectory shape amon
Previous methods for Learning from Demonstration leverage several approaches for a human to teach motions to a robot, including teleoperation, kinesthetic teaching, and natural demonstrations. However, little previous work has explored more general interfaces that allow for multiple demonstration ty
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 the environment are relevant before determining how these features should be used to compute reward. In particularly compl…
Interactive preference learning systems infer human preferences by presenting queries as pairs of options and collecting binary choices. Although binary choices are simple and widely used, they provide limited information about preference strength. To address this, we leverage human response times,…
Grounding the common-sense reasoning of Large Language Models in physical domains remains a pivotal yet unsolved problem for embodied AI. Whereas prior works have focused on leveraging LLMs directly for planning in symbolic spaces, this work uses LLMs to guide the search of task structures and const…
We describe a framework for using natural language to design state abstractions for imitation learning. Generalizable policy learning in high-dimensional observation spaces is facilitated by well-designed state representations, which can surface important features of an environment and hide irreleva…
Policies often fail at test-time due to *distribution shifts*---changes in the state and reward that occur when an end user deploys the policy in environments different from those seen in training. Data augmentation can help models be more robust to such shifts by varying specific concepts in the st…
Neural networks often learn task-specific latent representations that fail to generalize to novel settings or tasks. Conversely, humans learn discrete representations (i.e., concepts or words) at a variety of abstraction levels (e.g., "bird" vs. "sparrow'") and use the appropriate abstraction based…
In reinforcement learning (RL), a reward function that aligns exactly with a task's true performance metric is often necessarily sparse. For example, a true task metric might encode a reward of 1 upon success and 0 otherwise. The sparsity of these true task metrics can make them hard to learn from,…
Collaborative tasks often begin with partial task knowledge and incomplete plans from each partner. To complete these tasks, partners need to engage in situated communication with their partners and coordinate their partial plans towards a complete plan to achieve a joint task goal. While such c…
Despite recent success of deep learning models in research settings, their application in sensitive domains remains limited because of their opaque decision-making processes. Taking to this challenge, people have proposed various eXplainable AI (XAI) techniques designed to calibrate trust and unders…
Feature attribution methods are popular in interpretable machine learning. These methods compute the attribution of each input feature to represent its importance, but there is no consensus on the definition of "attribution", leading to many competing methods with little systematic evaluation, compl…
Interpretability methods are developed to understand the working mechanisms of black-box models, which is crucial to their responsible deployment. Fulfilling this goal requires both that the explanations generated by these methods are correct and that people can easily and reliably understand them.…
Learning from demonstration (LfD) has successfully solved tasks featuring a long time horizon. However, when the problem complexity also includes human-in-the-loop perturbations, state-of-the-art approaches do not guarantee the successful reproduction of a task. In this work, we identify the roots o…
Emergent communication (EC) research often focuses on optimizing task-specific utility as a driver for communication. However, there is increasing evidence that human languages are shaped by task-general communicative constraints and evolve under pressure to optimize the Information Bottleneck (IB)…
Recent causal probing literature reveals when language models and syntactic probes use similar representations. Such techniques may yield “false negative” causality results: models may use representations of syntax, but probes may have learned to use redundant encodings of the same syntactic informa…
Post-hoc explanation methods are gaining popularity for interpreting, understanding, and debugging neural networks. Most analyses using such methods explain decisions in response to inputs drawn from the test set. However, the test set may have few examples that trigger some model behaviors, such a…
Neural agents trained in reinforcement learning settings can learn to communicate among themselves via discrete tokens, accomplishing as a team what agents would be unable to do alone. However, the current standard of using one-hot vectors as discrete communication tokens prevents agents from acquir…
As robots are deployed in complex situations, engineers and end users must develop a holistic understanding of their behaviors, capabilities, and limitations. Some behaviors are directly optimized by the objective function. They often include success rate, completion time or energy consumption. Othe…
Reward engineering is crucial to high performance in reinforcement learning systems. Prior research into reward design has largely focused on Markovian functions representing the reward. While there has been research into expressing non-Markov rewards as linear temporal logic (LTL) formulas, this ha
We conducted a study to investigate trust in and dependence upon robotic decision support among nurses and doctors on a labor and delivery floor. There is evidence that suggestions provided by embodied agents engender inappropriate degrees of trust and reliance among humans. This concern is a critic…