123 citations · 406 across the 18 of their papers we have counts for
9 papers · 1 filter
Humans decompose tasks by trading off utility and computational cost
Carlos G. Correa, Mark K. Ho, Frederick Callaway +2
Human behavior emerges from planning over elaborate decompositions of tasks into goals, subgoals, and low-level actions. How are these decompositions created and used? Here, we pro…
How to talk so AI will learn: Instructions, descriptions, and autonomy
Theodore R Sumers, Robert D Hawkins, Mark K Ho +2
From the earliest years of our lives, humans use language to express our beliefs and desires. Being able to talk to artificial agents about our preferences would thus fulfill a cen…
Linguistic communication as (inverse) reward design
Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho +2
Natural language is an intuitive and expressive way to communicate reward information to autonomous agents. It encompasses everything from concrete instructions to abstract descrip…
Cognitive science as a source of forward and inverse models of human decisions for robotics and control
Mark K. Ho, Thomas L. Griffiths
Those designing autonomous systems that interact with humans will invariably face questions about how humans think and make decisions. Fortunately, computational cognitive science…
People construct simplified mental representations to plan
Mark K. Ho, David Abel, Carlos G. Correa +3
One of the most striking features of human cognition is the capacity to plan. Two aspects of human planning stand out: its efficiency and flexibility. Efficiency is especially impr…
Learning Rewards from Linguistic Feedback
Theodore R. Sumers, Mark K. Ho, Robert D. Hawkins +2
We explore unconstrained natural language feedback as a learning signal for artificial agents. Humans use rich and varied language to teach, yet most prior work on interactive lear…
Resource-rational Task Decomposition to Minimize Planning Costs
Carlos G. Correa, Mark K. Ho, Fred Callaway +1
People often plan hierarchically. That is, rather than planning over a monolithic representation of a task, they decompose the task into simpler subtasks and then plan to accomplis…
The Efficiency of Human Cognition Reflects Planned Information Processing
Mark K. Ho, David Abel, Jonathan D. Cohen +2
Planning is useful. It lets people take actions that have desirable long-term consequences. But, planning is hard. It requires thinking about consequences, which consumes limited c…
Interactive Learning from Policy-Dependent Human Feedback
James MacGlashan, Mark K Ho, Robert Loftin +5
This paper investigates the problem of interactively learning behaviors communicated by a human teacher using positive and negative feedback. Much previous work on this problem has…