Timezone: »
Human can leverage prior experience and learn novel tasks from a handful of demonstrations. In contrast to offline meta-reinforcement learning, which aims to achieve quick adaptation through better algorithm design, we investigate the effect of architecture inductive bias on the few-shot learning capability. We propose a Prompt-based Decision Transformer (Prompt-DT), which leverages the sequential modeling ability of the Transformer architecture and the prompt framework to achieve few-shot adaptation in offline RL. We design the trajectory prompt, which contains segments of the few-shot demonstrations, and encodes task-specific information to guide policy generation. Our experiments in five MuJoCo control benchmarks show that Prompt-DT is a strong few-shot learner without any extra finetuning on unseen target tasks. Prompt-DT outperforms its variants and strong meta offline RL baselines by a large margin with a trajectory prompt containing only a few timesteps. Prompt-DT is also robust to prompt length changes and can generalize to out-of-distribution (OOD) environments. Project page: \href{https://mxu34.github.io/PromptDT/}{https://mxu34.github.io/PromptDT/}.
Author Information
Mengdi Xu (Carnegie Mellon University)
Yikang Shen (University of Montreal)
Shun Zhang (MIT-IBM Watson AI Lab)
Yuchen Lu (Mila & University of Montreal)
Ding Zhao (Carnegie Mellon University)
Josh Tenenbaum (MIT)
Joshua Brett Tenenbaum is Professor of Cognitive Science and Computation at the Massachusetts Institute of Technology. He is known for contributions to mathematical psychology and Bayesian cognitive science. He previously taught at Stanford University, where he was the Wasow Visiting Fellow from October 2010 to January 2011. Tenenbaum received his undergraduate degree in physics from Yale University in 1993, and his Ph.D. from MIT in 1999. His work primarily focuses on analyzing probabilistic inference as the engine of human cognition and as a means to develop machine learning.
Chuang Gan (Umass Amherst/ IBM)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Spotlight: Prompting Decision Transformer for Few-Shot Policy Generalization »
Tue. Jul 19th 03:35 -- 03:40 PM Room Hall F
More from the Same Authors
-
2022 : Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables »
Mengdi Xu · Peide Huang · Visak Kumar · Jielin Qiu · Chao Fang · Kuan-Hui Lee · Xuewei Qi · Henry Lam · Bo Li · Ding Zhao -
2023 : Neuro-Symbolic Models of Human Moral Judgment: LLMs as Automatic Feature Extractors »
joseph kwon · Sydney Levine · Josh Tenenbaum -
2023 : Neuro-Symbolic Models of Human Moral Judgment: LLMs as Automatic Feature Extractors »
joseph kwon · Sydney Levine · Josh Tenenbaum -
2023 : Neuro-Symbolic Models of Human Moral Judgment: LLMs as Automatic Feature Extractors »
joseph kwon · Sydney Levine · Josh Tenenbaum -
2023 : Building Community Driven Libraries of Natural Programs »
Leonardo Hernandez Cano · Yewen Pu · Robert Hawkins · Josh Tenenbaum · Armando Solar-Lezama -
2023 : Visual-based Policy Learning with Latent Language Encoding »
Jielin Qiu · Mengdi Xu · William Han · Bo Li · Ding Zhao -
2023 : Can Brain Signals Reveal Inner Alignment with Human Languages? »
Jielin Qiu · William Han · Jiacheng Zhu · Mengdi Xu · Douglas Weber · Bo Li · Ding Zhao -
2023 : Inferring the Future by Imagining the Past »
Kartik Chandra · Tony Chen · Tzu-Mao Li · Jonathan Ragan-Kelley · Josh Tenenbaum -
2023 : Inferring the Goals of Communicating Agents from Actions and Instructions »
Lance Ying · Tan Zhi-Xuan · Vikash Mansinghka · Josh Tenenbaum -
2023 : The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling probabilistic social inferences from linguistic inputs »
Lance Ying · Katie Collins · Megan Wei · Cedegao Zhang · Tan Zhi-Xuan · Adrian Weller · Josh Tenenbaum · Catherine Wong -
2023 : Inferring the Future by Imagining the Past »
Kartik Chandra · Tony Chen · Tzu-Mao Li · Jonathan Ragan-Kelley · Josh Tenenbaum -
2023 Oral: Inferring Relational Potentials in Interacting Systems »
Armand Comas · Yilun Du · Christian Fernandez Lopez · Sandesh Ghimire · Mario Sznaier · Josh Tenenbaum · Octavia Camps -
2023 Poster: On the Complexity of Bayesian Generalization »
Yu-Zhe Shi · Manjie Xu · John Hopcroft · Kun He · Josh Tenenbaum · Song-Chun Zhu · Ying Nian Wu · Wenjuan Han · Yixin Zhu -
2023 Poster: Reparameterized Policy Learning for Multimodal Trajectory Optimization »
Zhiao Huang · Litian Liang · Zhan Ling · Xuanlin Li · Chuang Gan · Hao Su -
2023 Poster: Inferring Relational Potentials in Interacting Systems »
Armand Comas · Yilun Du · Christian Fernandez Lopez · Sandesh Ghimire · Mario Sznaier · Josh Tenenbaum · Octavia Camps -
2023 Poster: On the Forward Invariance of Neural ODEs »
Wei Xiao · Johnson Tsun-Hsuan Wang · Ramin Hasani · Mathias Lechner · Yutong Ban · Chuang Gan · Daniela Rus -
2023 Oral: Reparameterized Policy Learning for Multimodal Trajectory Optimization »
Zhiao Huang · Litian Liang · Zhan Ling · Xuanlin Li · Chuang Gan · Hao Su -
2023 Poster: Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC »
Yilun Du · Conor Durkan · Robin Strudel · Josh Tenenbaum · Sander Dieleman · Rob Fergus · Jascha Sohl-Dickstein · Arnaud Doucet · Will Grathwohl -
2023 Poster: Learning Neural Constitutive Laws from Motion Observations for Generalizable PDE Dynamics »
Pingchuan Ma · Peter Yichen Chen · Bolei Deng · Josh Tenenbaum · Tao Du · Chuang Gan · Wojciech Matusik -
2022 Poster: Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning »
Aviv Netanyahu · Tianmin Shu · Josh Tenenbaum · Pulkit Agrawal -
2022 Spotlight: Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning »
Aviv Netanyahu · Tianmin Shu · Josh Tenenbaum · Pulkit Agrawal -
2022 Poster: Planning with Diffusion for Flexible Behavior Synthesis »
Michael Janner · Yilun Du · Josh Tenenbaum · Sergey Levine -
2022 Oral: Planning with Diffusion for Flexible Behavior Synthesis »
Michael Janner · Yilun Du · Josh Tenenbaum · Sergey Levine -
2022 Poster: Learning Iterative Reasoning through Energy Minimization »
Yilun Du · Shuang Li · Josh Tenenbaum · Igor Mordatch -
2022 Spotlight: Learning Iterative Reasoning through Energy Minimization »
Yilun Du · Shuang Li · Josh Tenenbaum · Igor Mordatch -
2021 Poster: Global Prosody Style Transfer Without Text Transcriptions »
Kaizhi Qian · Yang Zhang · Shiyu Chang · Jinjun Xiong · Chuang Gan · David Cox · Mark Hasegawa-Johnson -
2021 Oral: Global Prosody Style Transfer Without Text Transcriptions »
Kaizhi Qian · Yang Zhang · Shiyu Chang · Jinjun Xiong · Chuang Gan · David Cox · Mark Hasegawa-Johnson -
2021 Poster: A large-scale benchmark for few-shot program induction and synthesis »
Ferran Alet · Javier Lopez-Contreras · James Koppel · Maxwell Nye · Armando Solar-Lezama · Tomas Lozano-Perez · Leslie Kaelbling · Josh Tenenbaum -
2021 Spotlight: A large-scale benchmark for few-shot program induction and synthesis »
Ferran Alet · Javier Lopez-Contreras · James Koppel · Maxwell Nye · Armando Solar-Lezama · Tomas Lozano-Perez · Leslie Kaelbling · Josh Tenenbaum -
2021 Poster: Adversarial Option-Aware Hierarchical Imitation Learning »
Mingxuan Jing · Wenbing Huang · Fuchun Sun · Xiaojian Ma · Tao Kong · Chuang Gan · Lei Li -
2021 Poster: AGENT: A Benchmark for Core Psychological Reasoning »
Tianmin Shu · Abhishek Bhandwaldar · Chuang Gan · Kevin Smith · Shari Liu · Dan Gutfreund · Elizabeth Spelke · Josh Tenenbaum · Tomer Ullman -
2021 Spotlight: AGENT: A Benchmark for Core Psychological Reasoning »
Tianmin Shu · Abhishek Bhandwaldar · Chuang Gan · Kevin Smith · Shari Liu · Dan Gutfreund · Elizabeth Spelke · Josh Tenenbaum · Tomer Ullman -
2021 Spotlight: Adversarial Option-Aware Hierarchical Imitation Learning »
Mingxuan Jing · Wenbing Huang · Fuchun Sun · Xiaojian Ma · Tao Kong · Chuang Gan · Lei Li -
2021 Poster: Improved Contrastive Divergence Training of Energy-Based Models »
Yilun Du · Shuang Li · Josh Tenenbaum · Igor Mordatch -
2021 Poster: Leveraging Language to Learn Program Abstractions and Search Heuristics »
Catherine Wong · Kevin Ellis · Josh Tenenbaum · Jacob Andreas -
2021 Spotlight: Leveraging Language to Learn Program Abstractions and Search Heuristics »
Catherine Wong · Kevin Ellis · Josh Tenenbaum · Jacob Andreas -
2021 Spotlight: Improved Contrastive Divergence Training of Energy-Based Models »
Yilun Du · Shuang Li · Josh Tenenbaum · Igor Mordatch -
2020 Poster: Visual Grounding of Learned Physical Models »
Yunzhu Li · Toru Lin · Kexin Yi · Daniel Bear · Daniel Yamins · Jiajun Wu · Josh Tenenbaum · Antonio Torralba -
2020 Poster: Countering Language Drift with Seeded Iterated Learning »
Yuchen Lu · Soumye Singhal · Florian Strub · Aaron Courville · Olivier Pietquin -
2019 Poster: Learning to Infer Program Sketches »
Maxwell Nye · Luke Hewitt · Josh Tenenbaum · Armando Solar-Lezama -
2019 Oral: Learning to Infer Program Sketches »
Maxwell Nye · Luke Hewitt · Josh Tenenbaum · Armando Solar-Lezama -
2019 Poster: Infinite Mixture Prototypes for Few-shot Learning »
Kelsey Allen · Evan Shelhamer · Hanul Shin · Josh Tenenbaum -
2019 Oral: Infinite Mixture Prototypes for Few-shot Learning »
Kelsey Allen · Evan Shelhamer · Hanul Shin · Josh Tenenbaum -
2019 Poster: Neurally-Guided Structure Inference »
Sidi Lu · Jiayuan Mao · Josh Tenenbaum · Jiajun Wu -
2019 Oral: Neurally-Guided Structure Inference »
Sidi Lu · Jiayuan Mao · Josh Tenenbaum · Jiajun Wu -
2018 Invited Talk: Building Machines that Learn and Think Like People »
Josh Tenenbaum