Timezone: »
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 biases, agents trained by meta-learning may sometimes acquire very different strategies from humans. We show that co-training these agents on predicting representations from natural language task descriptions and programs induced to generate such tasks guides them toward more human-like inductive biases. Human-generated language descriptions and program induction models that add new learned primitives both contain abstract concepts that can compress description length. Co-training on these representations result in more human-like behavior in downstream meta-reinforcement learning agents than less abstract controls (synthetic language descriptions, program induction without learned primitives), suggesting that the abstraction supported by these representations is key.
Author Information
Sreejan Kumar (Princeton University)
Carlos G. Correa (Princeton University)
I'm a grad student at the Princeton Neuroscience Institute, studying decision making and planning by using computational models to predict human behavior. I'm advised by Nathaniel Daw and Tom Griffiths.
Ishita Dasgupta (DeepMind)
Raja Marjieh (Princeton University)
Michael Y Hu (Princeton University)
Robert Hawkins (Princeton University)
Jonathan D Cohen (Princeton University)
nathaniel daw (Princeton University)
Karthik Narasimhan (Princeton University)
Tom Griffiths (Princeton University)
More from the Same Authors
-
2020 : Meta-Learning of Compositional Task Distributions in Humans and Machines »
Sreejan Kumar -
2021 Spotlight: Safe Reinforcement Learning with Natural Language Constraints »
Tsung-Yen Yang · Michael Y Hu · Yinlam Chow · Peter J. Ramadge · Karthik Narasimhan -
2021 : Meta-learning inductive biases of learning systems with Gaussian processes »
Michael Li · Erin Grant · Tom Griffiths -
2022 : Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement »
Michael Chang · Alyssa L Dayan · Franziska Meier · Tom Griffiths · Sergey Levine · Amy Zhang -
2022 : Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement »
Michael Chang · Alyssa L Dayan · Franziska Meier · Tom Griffiths · Sergey Levine · Amy Zhang -
2022 : Transformers generalize differently from information stored in context vs in weights »
Stephanie Chan · Ishita Dasgupta · Junkyung Kim · Dharshan Kumaran · Andrew Lampinen · Felix Hill -
2022 : REACT: Synergizing Reasoning and Acting in Language Models »
Shunyu Yao · Jeffrey Zhao · Dian Yu · Izhak Shafran · Karthik Narasimhan · Yuan Cao -
2022 : Collaborating with language models for embodied reasoning »
Ishita Dasgupta · Christine Kaeser-Chen · Kenneth Marino · Arun Ahuja · Sheila Babayan · Felix Hill · Rob Fergus -
2022 : Towards an Enhanced, Faithful, and Adaptable Web Interaction Environment »
John Yang · Howard Chen · Karthik Narasimhan -
2022 : Collaborating with language models for embodied reasoning »
Ishita Dasgupta · Christine Kaeser-Chen · Kenneth Marino · Arun Ahuja · Sheila Babayan · Felix Hill · Rob Fergus -
2022 : How to talk so AI will learn: instructions, descriptions, and pragmatics »
Theodore Sumers · Robert Hawkins · Mark Ho · Tom Griffiths · Dylan Hadfield-Menell -
2022 : Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement »
Michael Chang · Alyssa L Dayan · Franziska Meier · Tom Griffiths · Sergey Levine · Amy Zhang -
2022 : Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement »
Michael Chang · Alyssa L Dayan · Franziska Meier · Tom Griffiths · Sergey Levine · Amy Zhang -
2022 : When to choose: The role of information seeking in the speed-accuracy tradeoff »
Javier Alejandro Masís Obando · David Melnikoff · Lisa Feldman Barrett · Jonathan D Cohen -
2022 : Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement »
Michael Chang · Alyssa L Dayan · Franziska Meier · Tom Griffiths · Sergey Levine · Amy Zhang -
2022 : Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement »
Michael Chang · Alyssa L Dayan · Franziska Meier · Tom Griffiths · Sergey Levine · Amy Zhang -
2022 : Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement »
Michael Chang · Alyssa L Dayan · Franziska Meier · Tom Griffiths · Sergey Levine · Amy Zhang -
2022 : On the informativeness of supervision signals »
Ilia Sucholutsky · Raja Marjieh · Tom Griffiths -
2023 Poster: Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis »
Alexander Meulemans · Simon Schug · Seijin Kobayashi · nathaniel daw · Gregory Wayne -
2023 Poster: Reflexion: language agents with verbal reinforcement learning »
Noah Shinn · Federico Cassano · Ashwin Gopinath · Karthik Narasimhan · Shunyu Yao -
2023 Poster: Alignment with human representations supports robust few-shot learning »
Ilia Sucholutsky · Tom Griffiths -
2023 Poster: Passive learning of active causal strategies in agents and language models »
Andrew Lampinen · Stephanie Chan · Ishita Dasgupta · Andrew Nam · Jane Wang -
2023 Poster: Systematic Visual Reasoning through Object-Centric Relational Abstraction »
Taylor Webb · Shanka Subhra Mondal · Jonathan D Cohen -
2023 Poster: Tree of Thoughts: Deliberate Problem Solving with Large Language Models »
Shunyu Yao · Dian Yu · Jeffrey Zhao · Izhak Shafran · Tom Griffiths · Yuan Cao · Karthik Narasimhan -
2023 Poster: Im-Promptu: In-Context Composition from Image Prompts »
Bhishma Dedhia · Michael Chang · Jake Snell · Tom Griffiths · Niraj Jha -
2023 Poster: Gaussian Process Probes (GPP) for Uncertainty-Aware Probing »
Alexander Ku · Zi Wang · Jason Baldridge · Tom Griffiths · Been Kim -
2023 Poster: InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback »
John Yang · Akshara Prabhakar · Karthik Narasimhan · Shunyu Yao -
2023 Oral: Tree of Thoughts: Deliberate Problem Solving with Large Language Models »
Shunyu Yao · Dian Yu · Jeffrey Zhao · Izhak Shafran · Tom Griffiths · Yuan Cao · Karthik Narasimhan -
2022 Spotlight: Lightning Talks 5A-4 »
Yangrui Chen · Zhiyang Chen · Liang Zhang · Hanqing Wang · Jiaqi Han · Shuchen Wu · shaohui peng · Ganqu Cui · Yoav Kolumbus · Noemi Elteto · Xing Hu · Anwen Hu · Wei Liang · Cong Xie · Lifan Yuan · Noam Nisan · Wenbing Huang · Yousong Zhu · Ishita Dasgupta · Luc V Gool · Tingyang Xu · Rui Zhang · Qin Jin · Zhaowen Li · Meng Ma · Bingxiang He · Yangyi Chen · Juncheng Gu · Wenguan Wang · Ke Tang · Yu Rong · Eric Schulz · Fan Yang · Wei Li · Zhiyuan Liu · Jiaming Guo · Yanghua Peng · Haibin Lin · Haixin Wang · Qi Yi · Maosong Sun · Ruizhi Chen · Chuan Wu · Chaoyang Zhao · Yibo Zhu · Liwei Wu · xishan zhang · Zidong Du · Rui Zhao · Jinqiao Wang · Ling Li · Qi Guo · Ming Tang · Yunji Chen -
2022 Spotlight: Learning Structure from the Ground up---Hierarchical Representation Learning by Chunking »
Shuchen Wu · Noemi Elteto · Ishita Dasgupta · Eric Schulz -
2022 Panel: Panel 2B-1: Using natural language… & Modeling Human Exploration… »
Sreejan Kumar · Marcel Binz -
2022 : On the informativeness of supervision signals »
Ilia Sucholutsky · Raja Marjieh · Tom Griffiths -
2022 : Karthik Narasimhan: Semantic Supervision for few-shot generalization and personalization »
Karthik Narasimhan -
2022 : Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement »
Michael Chang · Alyssa L Dayan · Franziska Meier · Tom Griffiths · Sergey Levine · Amy Zhang -
2022 Workshop: Shared Visual Representations in Human and Machine Intelligence (SVRHM) »
Arturo Deza · Joshua Peterson · N Apurva Ratan Murty · Tom Griffiths -
2022 Poster: WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents »
Shunyu Yao · Howard Chen · John Yang · Karthik Narasimhan -
2022 Poster: Learning Physics Constrained Dynamics Using Autoencoders »
Tsung-Yen Yang · Justinian Rosca · Karthik Narasimhan · Peter J. Ramadge -
2022 Poster: Learning to Navigate Wikipedia by Taking Random Walks »
Manzil Zaheer · Kenneth Marino · Will Grathwohl · John Schultz · Wendy Shang · Sheila Babayan · Arun Ahuja · Ishita Dasgupta · Christine Kaeser-Chen · Rob Fergus -
2022 Poster: How to talk so AI will learn: Instructions, descriptions, and autonomy »
Theodore Sumers · Robert Hawkins · Mark Ho · Tom Griffiths · Dylan Hadfield-Menell -
2022 Poster: Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation »
Michael Chang · Tom Griffiths · Sergey Levine -
2022 Poster: DataMUX: Data Multiplexing for Neural Networks »
Vishvak Murahari · Carlos Jimenez · Runzhe Yang · Karthik Narasimhan -
2022 Poster: Learning Structure from the Ground up---Hierarchical Representation Learning by Chunking »
Shuchen Wu · Noemi Elteto · Ishita Dasgupta · Eric Schulz -
2021 : Reinforcement learning: It's all in the mind »
Tom Griffiths -
2021 Workshop: Workshop on Human and Machine Decisions »
Daniel Reichman · Joshua Peterson · Kiran Tomlinson · Annie Liang · Tom Griffiths -
2021 : Opening remarks »
Tom Griffiths -
2021 : The Right Words for the Job: Coordinating on Task-Relevant Conventions via Bayesian Program Learning »
Robert Hawkins -
2021 : Exploring the Structure of Human Adjective Representations »
Karan Grewal · Joshua Peterson · Bill Thompson · Tom Griffiths -
2021 : Invited Talk 4 »
Tom Griffiths -
2021 Workshop: Shared Visual Representations in Human and Machine Intelligence »
Arturo Deza · Joshua Peterson · N Apurva Ratan Murty · Tom Griffiths -
2021 Oral: Passive attention in artificial neural networks predicts human visual selectivity »
Thomas Langlois · Haicheng Zhao · Erin Grant · Ishita Dasgupta · Tom Griffiths · Nori Jacoby -
2021 Poster: Safe Reinforcement Learning with Natural Language Constraints »
Tsung-Yen Yang · Michael Y Hu · Yinlam Chow · Peter J. Ramadge · Karthik Narasimhan -
2021 Poster: Passive attention in artificial neural networks predicts human visual selectivity »
Thomas Langlois · Haicheng Zhao · Erin Grant · Ishita Dasgupta · Tom Griffiths · Nori Jacoby -
2020 Workshop: Shared Visual Representations in Human and Machine Intelligence (SVRHM) »
Arturo Deza · Joshua Peterson · N Apurva Ratan Murty · Tom Griffiths -
2020 Poster: Gibbs Sampling with People »
Peter Harrison · Raja Marjieh · Federico G Adolfi · Pol van Rijn · Manuel Anglada-Tort · Ofer Tchernichovski · Pauline Larrouy-Maestri · Nori Jacoby -
2020 Oral: Gibbs Sampling with People »
Peter Harrison · Raja Marjieh · Federico G Adolfi · Pol van Rijn · Manuel Anglada-Tort · Ofer Tchernichovski · Pauline Larrouy-Maestri · Nori Jacoby -
2019 : Concluding Remarks & Prizes Ceremony »
Arturo Deza · Joshua Peterson · Apurva Ratan Murty · Tom Griffiths -
2019 : Tom Griffiths »
Tom Griffiths -
2019 : Opening Remarks »
Arturo Deza · Joshua Peterson · Apurva Ratan Murty · Tom Griffiths -
2019 Workshop: Shared Visual Representations in Human and Machine Intelligence »
Arturo Deza · Joshua Peterson · Apurva Ratan Murty · Tom Griffiths -
2019 Poster: Reconciling meta-learning and continual learning with online mixtures of tasks »
Ghassen Jerfel · Erin Grant · Tom Griffiths · Katherine Heller -
2019 Spotlight: Reconciling meta-learning and continual learning with online mixtures of tasks »
Ghassen Jerfel · Erin Grant · Tom Griffiths · Katherine Heller -
2019 Poster: On the Utility of Learning about Humans for Human-AI Coordination »
Micah Carroll · Rohin Shah · Mark Ho · Tom Griffiths · Sanjit Seshia · Pieter Abbeel · Anca Dragan -
2017 Poster: A graph-theoretic approach to multitasking »
Noga Alon · Daniel Reichman · Igor Shinkar · Tal Wagner · Sebastian Musslick · Jonathan D Cohen · Tom Griffiths · Biswadip dey · Kayhan Ozcimder -
2017 Oral: A graph-theoretic approach to multitasking »
Noga Alon · Daniel Reichman · Igor Shinkar · Tal Wagner · Sebastian Musslick · Jonathan D Cohen · Tom Griffiths · Biswadip dey · Kayhan Ozcimder -
2016 Poster: Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation »
Tejas Kulkarni · Karthik Narasimhan · Ardavan Saeedi · Josh Tenenbaum -
2015 Poster: A Theory of Decision Making Under Dynamic Context »
Michael Shvartsman · Vaibhav Srivastava · Jonathan D Cohen -
2008 Poster: Sequential effects: Superstition or rational behavior? »
Angela Yu · Jonathan D Cohen -
2008 Poster: Learning to Use Working Memory in Partially Observable Environments through Dopaminergic Reinforcement »
Michael Todd · Yael Niv · Jonathan D Cohen -
2008 Spotlight: Sequential effects: Superstition or rational behavior? »
Angela Yu · Jonathan D Cohen -
2008 Oral: Learning to Use Working Memory in Partially Observable Environments through Dopaminergic Reinforcement »
Michael Todd · Yael Niv · Jonathan D Cohen