activity
20192022
most citedOn the Utility of Learning about Humans for Human-AI Coordination

91 citations · 102 across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG2022

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…

cs.LG20222 cited

UniMASK: Unified Inference in Sequential Decision Problems

Micah Carroll, Orr Paradise, Jessy Lin +8

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same…

cs.LG20221 cited

Optimal Behavior Prior: Data-Efficient Human Models for Improved Human-AI Collaboration

Mesut Yang, Micah Carroll, Anca Dragan

AI agents designed to collaborate with people benefit from models that enable them to anticipate human behavior. However, realistic models tend to require vast amounts of human dat…

cs.LG20218 cited

Evaluating the Robustness of Collaborative Agents

Paul Knott, Micah Carroll, Sam Devlin +4

In order for agents trained by deep reinforcement learning to work alongside humans in realistic settings, we will need to ensure that the agents are \emph{robust}. Since the real…

cs.LG201991 cited

On the Utility of Learning about Humans for Human-AI Coordination

Micah Carroll, Rohin Shah, Mark K. Ho +4

While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Ag…