Timezone: »
Reasoning in a complex and ambiguous embodied environment is a key goal for Reinforcement Learning (RL) agents. While some sophisticated RL agents can successfully solve difficult tasks, they require a large amount of training data and often struggle to generalize to new unseen environments and new tasks. On the other hand, Large Scale Language Models (LSLMs) have exhibited strong reasoning ability and the ability to to adapt to new tasks through in-context learning. However, LSLMs do not inherently have the ability to interrogate or intervene on the environment. In this work, we investigate how to combine these complementary abilities in a single system consisting of three parts: a Planner, an Actor, and a Reporter. The Planner is a pre-trained language model that can issue commands to a simple embodied agent (the Actor), while the Reporter communicates with the Planner to inform its next command. We present a set of tasks that require reasoning, test this system's ability to generalize zero-shot and investigate failure cases, and demonstrate how components of this system can be trained with reinforcement-learning to improve performance.
Author Information
Ishita Dasgupta (DeepMind)
Christine Kaeser-Chen (Google Inc.)
Kenneth Marino (Carnegie Mellon University)
Arun Ahuja (DeepMind)
Sheila Babayan (DeepMind)
Felix Hill (Deepmind)
Rob Fergus (DeepMind / NYU)
Rob Fergus is an Associate Professor of Computer Science at the Courant Institute of Mathematical Sciences, New York University. He received a Masters in Electrical Engineering with Prof. Pietro Perona at Caltech, before completing a PhD with Prof. Andrew Zisserman at the University of Oxford in 2005. Before coming to NYU, he spent two years as a post-doc in the Computer Science and Artificial Intelligence Lab (CSAIL) at MIT, working with Prof. William Freeman. He has received several awards including a CVPR best paper prize, a Sloan Fellowship & NSF Career award and the IEEE Longuet-Higgins prize.
More from the Same Authors
-
2021 : Task-driven Discovery of Perceptual Schemas for Generalization in Reinforcement Learning »
Wilka Carvalho · Andrew Lampinen · Kyriacos Nikiforou · Felix Hill · Murray Shanahan -
2021 : Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning »
Denis Yarats · Rob Fergus · Alessandro Lazaric · Lerrel Pinto -
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 : Collaborating with language models for embodied reasoning »
Ishita Dasgupta · Christine Kaeser-Chen · Kenneth Marino · Arun Ahuja · Sheila Babayan · Felix Hill · Rob Fergus -
2023 Poster: NetHack is Hard to Hack »
Ulyana Piterbarg · Lerrel Pinto · Rob Fergus -
2023 Poster: The Transient Nature of Emergent In-context Learning in Transformers »
Aaditya Singh · Stephanie Chan · Ted Moskovitz · Erin Grant · Andrew Saxe · Felix Hill -
2023 Poster: Passive learning of active causal strategies in agents and language models »
Andrew Lampinen · Stephanie Chan · Ishita Dasgupta · Andrew Nam · Jane Wang -
2022 : Meaning without reference in large language models »
Steven Piantadosi · Felix Hill -
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 Poster: Using natural language and program abstractions to instill human inductive biases in machines »
Sreejan Kumar · Carlos G. Correa · Ishita Dasgupta · Raja Marjieh · Michael Y Hu · Robert Hawkins · Jonathan D Cohen · nathaniel daw · Karthik Narasimhan · Tom Griffiths -
2022 Poster: Data Distributional Properties Drive Emergent In-Context Learning in Transformers »
Stephanie Chan · Adam Santoro · Andrew Lampinen · Jane Wang · Aaditya Singh · Pierre Richemond · James McClelland · Felix Hill -
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: Semantic Exploration from Language Abstractions and Pretrained Representations »
Allison Tam · Neil Rabinowitz · Andrew Lampinen · Nicholas Roy · Stephanie Chan · DJ Strouse · Jane Wang · Andrea Banino · Felix Hill -
2022 Poster: Learning Structure from the Ground up---Hierarchical Representation Learning by Chunking »
Shuchen Wu · Noemi Elteto · Ishita Dasgupta · Eric Schulz -
2021 Poster: Attention over Learned Object Embeddings Enables Complex Visual Reasoning »
David Ding · Felix Hill · Adam Santoro · Malcolm Reynolds · Matt Botvinick -
2021 Poster: Multimodal Few-Shot Learning with Frozen Language Models »
Maria Tsimpoukelli · Jacob L Menick · Serkan Cabi · S. M. Ali Eslami · Oriol Vinyals · Felix Hill -
2021 Poster: Automatic Data Augmentation for Generalization in Reinforcement Learning »
Roberta Raileanu · Maxwell Goldstein · Denis Yarats · Ilya Kostrikov · Rob Fergus -
2021 Poster: Towards mental time travel: a hierarchical memory for reinforcement learning agents »
Andrew Lampinen · Stephanie Chan · Andrea Banino · Felix Hill -
2021 Oral: Attention over Learned Object Embeddings Enables Complex Visual Reasoning »
David Ding · Felix Hill · Adam Santoro · Malcolm Reynolds · Matt Botvinick -
2020 : Contributed Talk - Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences »
Alexander Rives · Siddharth Goyal · Joshua Meier · Zeming Lin · Demi Guo · Myle Ott · Larry Zitnick · Rob Fergus -
2019 : Poster Session »
Rishav Chourasia · Yichong Xu · Corinna Cortes · Chien-Yi Chang · Yoshihiro Nagano · So Yeon Min · Benedikt Boecking · Phi Vu Tran · Kamyar Ghasemipour · Qianggang Ding · Shouvik Mani · Vikram Voleti · Rasool Fakoor · Miao Xu · Kenneth Marino · Lisa Lee · Volker Tresp · Jean-Francois Kagy · Marvin Zhang · Barnabas Poczos · Dinesh Khandelwal · Adrien Bardes · Evan Shelhamer · Jiacheng Zhu · Ziming Li · Xiaoyan Li · Dmitrii Krasheninnikov · Ruohan Wang · Mayoore Jaiswal · Emad Barsoum · Suvansh Sanjeev · Theeraphol Wattanavekin · Qizhe Xie · Sifan Wu · Yuki Yoshida · David Kanaa · Sina Khoshfetrat Pakazad · Mehdi Maasoumy -
2018 Poster: Neural Arithmetic Logic Units »
Andrew Trask · Felix Hill · Scott Reed · Jack Rae · Chris Dyer · Phil Blunsom -
2017 : Poster Session 2 »
Farhan Shafiq · Antonio Tomas Nevado Vilchez · Takato Yamada · Sakyasingha Dasgupta · Robin Geyer · Moin Nabi · Crefeda Rodrigues · Edoardo Manino · Alexantrou Serb · Miguel A. Carreira-Perpinan · Kar Wai Lim · Bryan Kian Hsiang Low · Rohit Pandey · Marie C White · Pavel Pidlypenskyi · Xue Wang · Christine Kaeser-Chen · Michael Zhu · Suyog Gupta · Sam Leroux -
2017 : Panel Discussion »
Felix Hill · Olivier Pietquin · Jack Gallant · Raymond Mooney · Sanja Fidler · Chen Yu · Devi Parikh -
2017 : Grounded Language Learning in a Simulated 3D World »
Felix Hill -
2016 Poster: Learning Multiagent Communication with Backpropagation »
Sainbayar Sukhbaatar · arthur szlam · Rob Fergus -
2014 Poster: Depth Map Prediction from a Single Image using a Multi-Scale Deep Network »
David Eigen · Christian Puhrsch · Rob Fergus -
2014 Poster: Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation »
Emily Denton · Wojciech Zaremba · Joan Bruna · Yann LeCun · Rob Fergus -
2014 Spotlight: Depth Map Prediction from a Single Image using a Multi-Scale Deep Network »
David Eigen · Christian Puhrsch · Rob Fergus -
2014 Poster: Learning to Discover Efficient Mathematical Identities »
Wojciech Zaremba · Karol Kurach · Rob Fergus -
2014 Spotlight: Learning to Discover Efficient Mathematical Identities »
Wojciech Zaremba · Karol Kurach · Rob Fergus -
2013 Tutorial: Deep Learning for Computer Vision »
Rob Fergus -
2011 Workshop: Machine Learning meets Computational Photography »
Michael Hirsch · Stefan Harmeling · Rob Fergus · Peyman Milanfar -
2011 Poster: Facial Expression Transfer with Input-Output Temporal Restricted Boltzmann Machines »
Matthew D Zeiler · Graham Taylor · Leonid Sigal · Iain Matthews · Rob Fergus -
2011 Session: Spotlight Session 1 »
Rob Fergus -
2010 Session: Oral Session 17 »
Rob Fergus -
2010 Poster: Pose-Sensitive Embedding by Nonlinear NCA Regression »
Graham Taylor · Rob Fergus · George Williams · Ian Spiro · Christoph Bregler -
2009 Poster: Fast Image Deconvolution using Hyper-Laplacian Priors »
Dilip Krishnan · Rob Fergus -
2009 Spotlight: Fast Image Deconvolution using Hyper-Laplacian Priors »
Dilip Krishnan · Rob Fergus -
2009 Poster: Semi-Supervised Learning in Gigantic Image Collections »
Rob Fergus · Yair Weiss · Antonio Torralba -
2009 Oral: Semi-Supervised Learning in Gigantic Image Collections »
Rob Fergus · Yair Weiss · Antonio Torralba -
2008 Poster: Spectral Hashing »
Yair Weiss · Antonio Torralba · Rob Fergus -
2007 Spotlight: Object Recognition by Scene Alignment »
Bryan C Russell · Antonio Torralba · Ce Liu · Rob Fergus · William Freeman -
2007 Poster: Object Recognition by Scene Alignment »
Bryan C Russell · Antonio Torralba · Ce Liu · Rob Fergus · William Freeman