65 citations · 220 across the 17 of their papers we have counts for
13 papers · 1 filter
Unifying Grokking and Double Descent
Xander Davies, Lauro Langosco, David Krueger
A principled understanding of generalization in deep learning may require unifying disparate observations under a single conceptual framework. Previous work has studied \emph{grokk…
Investigating the role of model-based learning in exploration and transfer
Jacob Walker, Eszter Vértes, Yazhe Li +4
State of the art reinforcement learning has enabled training agents on tasks of ever increasing complexity. However, the current paradigm tends to favor training agents from scratc…
Towards Understanding How Machines Can Learn Causal Overhypotheses
Eliza Kosoy, David M. Chan, Adrian Liu +7
Recent work in machine learning and cognitive science has suggested that understanding causal information is essential to the development of intelligence. The extensive literature…
Learning Causal Overhypotheses through Exploration in Children and Computational Models
Eliza Kosoy, Adrian Liu, Jasmine Collins +7
Despite recent progress in reinforcement learning (RL), RL algorithms for exploration still remain an active area of research. Existing methods often focus on state-based metrics,…
Physical Design using Differentiable Learned Simulators
Kelsey R. Allen, Tatiana Lopez-Guevara, Kimberly Stachenfeld +4
Designing physical artifacts that serve a purpose - such as tools and other functional structures - is central to engineering as well as everyday human behavior. Though automating…
Procedural Generalization by Planning with Self-Supervised World Models
Ankesh Anand, Jacob Walker, Yazhe Li +5
One of the key promises of model-based reinforcement learning is the ability to generalize using an internal model of the world to make predictions in novel environments and tasks.…
Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning
Giambattista Parascandolo, Lars Buesing, Josh Merel +6
Standard planners for sequential decision making (including Monte Carlo planning, tree search, dynamic programming, etc.) are constrained by an implicit sequential planning assumpt…
Combining Q-Learning and Search with Amortized Value Estimates
Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez +4
We introduce "Search with Amortized Value Estimates" (SAVE), an approach for combining model-free Q-learning with model-based Monte-Carlo Tree Search (MCTS). In SAVE, a learned pri…
Object-oriented state editing for HRL
Victor Bapst, Alvaro Sanchez-Gonzalez, Omar Shams +4
We introduce agents that use object-oriented reasoning to consider alternate states of the world in order to more quickly find solutions to problems. Specifically, a hierarchical c…
Structured agents for physical construction
Victor Bapst, Alvaro Sanchez-Gonzalez, Carl Doersch +4
Physical construction---the ability to compose objects, subject to physical dynamics, to serve some function---is fundamental to human intelligence. We introduce a suite of challen…
Relational inductive bias for physical construction in humans and machines
Jessica B. Hamrick, Kelsey R. Allen, Victor Bapst +4
While current deep learning systems excel at tasks such as object classification, language processing, and gameplay, few can construct or modify a complex system such as a tower of…
Relational inductive biases, deep learning, and graph networks
Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst +24
Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, i…
Metacontrol for Adaptive Imagination-Based Optimization
Jessica B. Hamrick, Andrew J. Ballard, Razvan Pascanu +3
Many machine learning systems are built to solve the hardest examples of a particular task, which often makes them large and expensive to run---especially with respect to the easie…