Transformers are Sample-Efficient World Models

1 September 2022

Papers citing "Transformers are Sample-Efficient World Models"

34 / 134 papers shown

Title
Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning Fan Feng Sara Magliacane OffRL OCL 41 11 0 18 Jul 2023
Transformers in Reinforcement Learning: A Survey Pranav Agarwal A. Rahman P. St-Charles Simon J. D. Prince Samira Ebrahimi Kahou OffRL 35 19 0 12 Jul 2023
When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment Tianwei Ni Michel Ma Benjamin Eysenbach Pierre-Luc Bacon OffRL 28 35 0 07 Jul 2023
Facing Off World Model Backbones: RNNs, Transformers, and S4 Fei Deng Junyeong Park Sungjin Ahn 34 25 0 05 Jul 2023
MeLM, a generative pretrained language modeling framework that solves forward and inverse mechanics problems Markus J. Buehler AI4CE 39 41 0 30 Jun 2023
Curious Replay for Model-based Adaptation Isaac Kauvar Christopher Doyle Linqi Zhou Nick Haber 25 11 0 28 Jun 2023
PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning Hojoon Lee Hanseul Cho Hyunseung Kim Daehoon Gwak Joonkee Kim Jaegul Choo Se-Young Yun Chulhee Yun OffRL 82 26 0 19 Jun 2023
Recurrent Action Transformer with Memory A. Staroverov A. Bessonov Dmitry A. Yudin A. Kovalev Aleksandr I. Panov OffRL 43 4 0 15 Jun 2023
IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control Rohan Chitnis Yingchen Xu B. Hashemi Lucas Lehnert Ürün Dogan Zheqing Zhu Olivier Delalleau OffRL 34 9 0 01 Jun 2023
Bigger, Better, Faster: Human-level Atari with human-level efficiency Max Schwarzer J. Obando-Ceron Rameswar Panda Marc G. Bellemare Rishabh Agarwal Pablo Samuel Castro OffRL 54 85 0 30 May 2023
Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning Jialong Wu Haoyu Ma Chao Deng Mingsheng Long OffRL 38 25 0 29 May 2023
Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning Q. Wang Jun Yang Yunbo Wang Xin Jin Wenjun Zeng Xiaokang Yang OffRL OnRL 41 3 0 24 May 2023
A Generalist Dynamics Model for Control Ingmar Schubert Jingwei Zhang Jake Bruce Sarah Bechtle Emilio Parisotto Martin Riedmiller Jost Tobias Springenberg Arunkumar Byravan Leonard Hasenclever N. Heess AI4CE 41 30 0 18 May 2023
Generative Pretrained Autoregressive Transformer Graph Neural Network applied to the Analysis and Discovery of Novel Proteins Markus J. Buehler 30 21 0 07 May 2023
Representation Matters: The Game of Chess Poses a Challenge to Vision Transformers Johannes Czech Jannis Blüml Kristian Kersting ViT 58 0 0 28 Apr 2023
Modeling and design of heterogeneous hierarchical bioinspired spider web structures using generative deep learning and additive manufacturing Wei Lu Nicolas A. Lee Markus J. Buehler AI4CE 25 1 0 11 Apr 2023
Planning Goals for Exploration E. Hu Richard Chang Oleh Rybkin Dinesh Jayaraman 43 24 0 23 Mar 2023
Transformer-based World Models Are Happy With 100k Interactions Jan Robine Marc Höftmann Tobias Uelwer Stefan Harmeling OffRL 27 71 0 13 Mar 2023
ConBaT: Control Barrier Transformer for Safe Policy Learning Yue Meng Sai H. Vemprala Rogerio Bonatti Chuchu Fan Ashish Kapoor OffRL 45 3 0 07 Mar 2023
Foundation Models for Decision Making: Problems, Methods, and Opportunities Sherry Yang Ofir Nachum Yilun Du Jason W. Wei Pieter Abbeel Dale Schuurmans LM&Ro OffRL LRM AI4CE 98 156 0 07 Mar 2023
Learning Universal Policies via Text-Guided Video Generation Yilun Du Mengjiao Yang Bo Dai H. Dai Ofir Nachum J. Tenenbaum Dale Schuurmans Pieter Abbeel PINN LM&Ro 27 235 0 31 Jan 2023
SMART: Self-supervised Multi-task pretrAining with contRol Transformers Yanchao Sun Shuang Ma Ratnesh Madaan Rogerio Bonatti Furong Huang Ashish Kapoor 41 40 0 24 Jan 2023
Mastering Diverse Domains through World Models Danijar Hafner J. Pašukonis Jimmy Ba Timothy Lillicrap 38 559 0 10 Jan 2023
A Survey on Transformers in Reinforcement Learning Wenzhe Li Hao Luo Zichuan Lin Chongjie Zhang Zongqing Lu Deheng Ye OffRL MU AI4CE 37 56 0 08 Jan 2023
Transformer in Transformer as Backbone for Deep Reinforcement Learning Hangyu Mao Rui Zhao Hao Chen Jianye Hao Yiqun Chen Dong Li Junge Zhang Zhen Xiao OffRL 39 8 0 30 Dec 2022
On Transforming Reinforcement Learning by Transformer: The Development Trajectory Shengchao Hu Li Shen Ya Zhang Yixin Chen Dacheng Tao OffRL 32 25 0 29 Dec 2022
Contrastive Distillation Is a Sample-Efficient Self-Supervised Loss Policy for Transfer Learning Christopher T. Lengerich Gabriel Synnaeve Amy Zhang Hugh Leather Kurt Shuster Franccois Charton Charysse Redwood SSL OffRL 32 1 0 21 Dec 2022
Transformers Learn Shortcuts to Automata Bingbin Liu Jordan T. Ash Surbhi Goel A. Krishnamurthy Cyril Zhang OffRL LRM 50 158 0 19 Oct 2022
SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models Ziyi Wu Nikita Dvornik Klaus Greff Thomas Kipf Animesh Garg OCL BDL 67 91 0 12 Oct 2022
Light-weight probing of unsupervised representations for Reinforcement Learning Wancong Zhang Anthony GX-Chen Vlad Sobal Yann LeCun Nicolas Carion SSL OffRL 46 13 0 25 Aug 2022
MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned Anssi Kanervisto Stephanie Milani Karolis Ramanauskas Nicholay Topin Zichuan Lin ... Franccois Fleuret Alexander Nikulin Yury Belousov Oleg Svidchenko A. Shpilman OffRL 60 32 0 17 Feb 2022
Masked Autoencoders Are Scalable Vision Learners Kaiming He Xinlei Chen Saining Xie Yanghao Li Piotr Dollár Ross B. Girshick ViT TPM 322 7,503 0 11 Nov 2021
VideoGPT: Video Generation using VQ-VAE and Transformers Wilson Yan Yunzhi Zhang Pieter Abbeel A. Srinivas ViT VGen 245 487 0 20 Apr 2021
Zero-Shot Text-to-Image Generation Aditya A. Ramesh Mikhail Pavlov Gabriel Goh Scott Gray Chelsea Voss Alec Radford Mark Chen Ilya Sutskever VLM 257 4,816 0 24 Feb 2021