Publications (18)
Physical problem solving: Joint planning with symbolic, geometric, and dynamic constraints
Ilker Yildirim, Tobias Gerstenberg, Basil Saeed +2
In this paper, we present a new task that investigates how people interact with and make judgments about towers of blocks. In Experiment~1, participants in the lab solved a series…
At Human Speed: Deep Reinforcement Learning with Action Delay
Vlad Firoiu, Tina Ju, Josh Tenenbaum
There has been a recent explosion in the capabilities of game-playing artificial intelligence. Many classes of tasks, from video games to motor control to board games, are now solv…
Residual Policy Learning
Tom Silver, Kelsey Allen, Josh Tenenbaum +1
We present Residual Policy Learning (RPL): a simple method for improving nondifferentiable policies using model-free deep reinforcement learning. RPL thrives in complex robotic man…
When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment
Zhijing Jin, Sydney Levine, Fernando Gonzalez +6
AI systems are becoming increasingly intertwined with human life. In order to effectively collaborate with humans and ensure safety, AI systems need to be able to understand, inter…
Few-Shot Bayesian Imitation Learning with Logical Program Policies
Tom Silver, Kelsey R. Allen, Alex K. Lew +2
Humans can learn many novel tasks from a very small number (1--5) of demonstrations, in stark contrast to the data requirements of nearly tabula rasa deep learning methods. We prop…
Learning Evolved Combinatorial Symbols with a Neuro-symbolic Generative Model
Matthias Hofer, Tuan Anh Le, Roger Levy +1
Humans have the ability to rapidly understand rich combinatorial concepts from limited data. Here we investigate this ability in the context of auditory signals, which have been ev…
Learning a Hierarchical Planner from Humans in Multiple Generations
Leonardo Hernandez Cano, Yewen Pu, Robert D. Hawkins +2
A typical way in which a machine acquires knowledge from humans is by programming. Compared to learning from demonstrations or experiences, programmatic learning allows the machine…
Learning to Share and Hide Intentions using Information Regularization
DJ Strouse, Max Kleiman-Weiner, Josh Tenenbaum +2
Learning to cooperate with friends and compete with foes is a key component of multi-agent reinforcement learning. Typically to do so, one requires access to either a model of or i…
Logical Rule Induction and Theory Learning Using Neural Theorem Proving
Andres Campero, Aldo Pareja, Tim Klinger +2
A hallmark of human cognition is the ability to continually acquire and distill observations of the world into meaningful, predictive theories. In this paper we present a new mecha…
Inferring the Future by Imagining the Past
Kartik Chandra, Tony Chen, Tzu-Mao Li +2
A single panel of a comic book can say a lot: it can depict not only where the characters currently are, but also their motions, their motivations, their emotions, and what they mi…
Acting as Inverse Inverse Planning
Kartik Chandra, Tzu-Mao Li, Josh Tenenbaum +1
Great storytellers know how to take us on a journey. They direct characters to act -- not necessarily in the most rational way -- but rather in a way that leads to interesting situ…
Program Synthesis with Pragmatic Communication
Yewen Pu, Kevin Ellis, Marta Kryven +2
Program synthesis techniques construct or infer programs from user-provided specifications, such as input-output examples. Yet most specifications, especially those given by end-us…
Compositional Foundation Models for Hierarchical Planning
Anurag Ajay, Seungwook Han, Yilun Du +7
To make effective decisions in novel environments with long-horizon goals, it is crucial to engage in hierarchical reasoning across spatial and temporal scales. This entails planni…
Map Induction: Compositional spatial submap learning for efficient exploration in novel environments
Sugandha Sharma, Aidan Curtis, Marta Kryven +2
Humans are expert explorers. Understanding the computational cognitive mechanisms that support this efficiency can advance the study of the human mind and enable more efficient exp…
A Computational Model of Commonsense Moral Decision Making
Richard Kim, Max Kleiman-Weiner, Andres Abeliuk +4
We introduce a new computational model of moral decision making, drawing on a recent theory of commonsense moral learning via social dynamics. Our model describes moral dilemmas as…
Popularity and Performance: A Large-Scale Study
Peter Krafft, Julia Zheng, Erez Shmueli +3
Social scientists have long sought to understand why certain people, items, or options become more popular than others. One seemingly intuitive theory is that inherent value drives…
Write, Execute, Assess: Program Synthesis with a REPL
Kevin Ellis, Maxwell Nye, Yewen Pu +3
We present a neural program synthesis approach integrating components which write, execute, and assess code to navigate the search space of possible programs. We equip the search p…
Modeling human intention inference in continuous 3D domains by inverse planning and body kinematics
Yingdong Qian, Marta Kryven, Tao Gao +2
How to build AI that understands human intentions, and uses this knowledge to collaborate with people? We describe a computational framework for evaluating models of goal inference…