47 citations · 65 across the 5 of their papers we have counts for
5 papers
Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis
Alexander Meulemans, Simon Schug, Seijin Kobayashi +2
To make reinforcement learning more sample efficient, we need better credit assignment methods that measure an action's influence on future rewards. Building upon Hindsight Credit…
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…
Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning
Sreejan Kumar, Ishita Dasgupta, Nathaniel D. Daw +2
The ability to acquire abstract knowledge is a hallmark of human intelligence and is believed by many to be one of the core differences between humans and neural network models. Ag…
Meta-Learning of Structured Task Distributions in Humans and Machines
Sreejan Kumar, Ishita Dasgupta, Jonathan D. Cohen +2
In recent years, meta-learning, in which a model is trained on a family of tasks (i.e. a task distribution), has emerged as an approach to training neural networks to perform tasks…