TWIST: Teacher-Student World Model Distillation for Efficient Sim-to-Real Transfer

7 November 2023

Papers citing "TWIST: Teacher-Student World Model Distillation for Efficient Sim-to-Real Transfer"

24 / 24 papers shown

Title
COMBO-Grasp: Learning Constraint-Based Manipulation for Bimanual Occluded Grasping Jun Yamada Alexander L. Mitchell Jack Collins Ingmar Posner OffRL 135 0 0 17 Feb 2025
Reward-Free Curricula for Training Robust World Models Marc Rigter Minqi Jiang Ingmar Posner VLM OffRL 81 9 0 15 Jun 2023
Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments Mayank Mittal C. Yu Qinxi Yu Jingzhou Liu Nikita Rudin ... Ajay Mandlekar Buck Babich Gavriel State Marco Hutter Animesh Garg 111 208 0 10 Jan 2023
DayDreamer: World Models for Physical Robot Learning Philipp Wu Alejandro Escontrela Danijar Hafner Ken Goldberg Pieter Abbeel 110 299 0 28 Jun 2022
A System for General In-Hand Object Re-Orientation Tao Chen Jie Xu Pulkit Agrawal 112 257 0 04 Nov 2021
Deep Reinforcement Learning at the Edge of the Statistical Precipice Rishabh Agarwal Max Schwarzer Pablo Samuel Castro Aaron Courville Marc G. Bellemare OffRL 123 676 0 30 Aug 2021
Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing Axel Brunnbauer Luigi Berducci Andreas Brandstätter Mathias Lechner Ramin Hasani Daniela Rus Radu Grosu LM&Ro 61 38 0 08 Mar 2021
Generalization in Reinforcement Learning by Soft Data Augmentation Nicklas Hansen Xiaolong Wang OffRL 105 174 0 26 Nov 2020
Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learning M. Lutter Johannes Silberbauer Joe Watson Jan Peters OffRL 77 34 0 03 Nov 2020
Mastering Atari with Discrete World Models Danijar Hafner Timothy Lillicrap Mohammad Norouzi Jimmy Ba DRL 121 869 0 05 Oct 2020
Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey Wenshuai Zhao Jorge Peña Queralta Tomi Westerlund OffRL 201 742 0 24 Sep 2020
Dream to Control: Learning Behaviors by Latent Imagination Danijar Hafner Timothy Lillicrap Jimmy Ba Mohammad Norouzi VLM 130 1,371 0 03 Dec 2019
Attention-Privileged Reinforcement Learning Sasha Salter Dushyant Rao Markus Wulfmeier R. Hadsell Ingmar Posner 72 8 0 19 Nov 2019
Solving Rubik's Cube with a Robot Hand OpenAI Ilge Akkaya Marcin Andrychowicz Maciek Chociej Ma-teusz Litwin ... Peter Welinder Lilian Weng Qiming Yuan Wojciech Zaremba Lei Zhang ODL 121 1,232 0 16 Oct 2019
Learning to Walk via Deep Reinforcement Learning Tuomas Haarnoja Sehoon Ha Aurick Zhou Jie Tan George Tucker Sergey Levine 105 441 0 26 Dec 2018
Learning Latent Dynamics for Planning from Pixels Danijar Hafner Timothy Lillicrap Ian S. Fischer Ruben Villegas David R Ha Honglak Lee James Davidson BDL 92 1,446 0 12 Nov 2018
Learning Dexterous In-Hand Manipulation OpenAI OpenAI Marcin Andrychowicz Bowen Baker Maciek Chociej Rafal Jozefowicz ... Szymon Sidor Joshua Tobin Peter Welinder Lilian Weng Wojciech Zaremba 159 1,884 0 01 Aug 2018
World Models David R Ha Jürgen Schmidhuber SyDa 148 1,098 0 27 Mar 2018
DeepMind Control Suite Yuval Tassa Yotam Doron Alistair Muldal Tom Erez Yazhe Li ... A. Abdolmaleki J. Merel Andrew Lefrancq Timothy Lillicrap Martin Riedmiller ELM LM&Ro BDL 150 1,143 0 02 Jan 2018
Asymmetric Actor Critic for Image-Based Robot Learning Lerrel Pinto Marcin Andrychowicz Peter Welinder Wojciech Zaremba Pieter Abbeel OffRL 70 374 0 18 Oct 2017
Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World Joshua Tobin Rachel Fong Alex Ray Jonas Schneider Wojciech Zaremba Pieter Abbeel 259 2,972 0 20 Mar 2017
Policy Distillation Andrei A. Rusu Sergio Gomez Colmenarejo Çağlar Gülçehre Guillaume Desjardins J. Kirkpatrick Razvan Pascanu Volodymyr Mnih Koray Kavukcuoglu R. Hadsell 98 695 0 19 Nov 2015
Model Predictive Path Integral Control using Covariance Variable Importance Sampling Grady Williams Andrew Aldrich Evangelos Theodorou 72 151 0 03 Sep 2015
Playing Atari with Deep Reinforcement Learning Volodymyr Mnih Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra Martin Riedmiller 129 12,265 0 19 Dec 2013