123 citations · 192 across the 7 of their papers we have counts for
7 papers
Program-Based Strategy Induction for Reinforcement Learning
Carlos G. Correa, Thomas L. Griffiths, Nathaniel D. Daw
Typical models of learning assume incremental estimation of continuously-varying decision variables like expected rewards. However, this class of models fails to capture more idios…
Exploring the hierarchical structure of human plans via program generation
Carlos G. Correa, Sophia Sanborn, Mark K. Ho +3
Human behavior is often assumed to be hierarchically structured, made up of abstract actions that can be decomposed into concrete actions. However, behavior is typically measured a…
Structurally guided task decomposition in spatial navigation tasks
Ruiqi He, Carlos G. Correa, Thomas L. Griffiths +1
How are people able to plan so efficiently despite limited cognitive resources? We aimed to answer this question by extending an existing model of human task decomposition that can…
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…
Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines
Sreejan Kumar, Carlos G. Correa, Ishita Dasgupta +7
Strong inductive biases give humans the ability to quickly learn to perform a variety of tasks. Although meta-learning is a method to endow neural networks with useful inductive bi…
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…
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…