Planning to Explore via Self-Supervised World Models

12 May 2020

Pieter Abbeel

Papers citing "Planning to Explore via Self-Supervised World Models"

47 / 97 papers shown

Title
Task-Agnostic Learning to Accomplish New Tasks Xianqi Zhang Xingtao Wang Xu Liu Wenrui Wang Xiaopeng Fan Debin Zhao OffRL 88 0 0 09 Sep 2022
Cell-Free Latent Go-Explore Quentin Gallouedec Emmanuel Dellandrea 14 1 0 31 Aug 2022
Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and Explorations Xufeng Zhao C. Weber Muhammad Burhan Hafez S. Wermter 18 8 0 04 Aug 2022
DayDreamer: World Models for Physical Robot Learning Philipp Wu Alejandro Escontrela Danijar Hafner Ken Goldberg Pieter Abbeel 55 277 0 28 Jun 2022
BYOL-Explore: Exploration by Bootstrapped Prediction Z. Guo S. Thakoor Miruna Pislar Bernardo Avila-Pires Florent Altché ... Yunhao Tang Michal Valko Rémi Munos M. G. Azar Bilal Piot 22 68 0 16 Jun 2022
Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity Alekh Agarwal Tong Zhang 47 22 0 15 Jun 2022
Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning Remo Sasso M. Sabatelli M. Wiering 49 9 0 28 May 2022
Reward Uncertainty for Exploration in Preference-based Reinforcement Learning Xinran Liang Katherine Shu Kimin Lee Pieter Abbeel 21 58 0 24 May 2022
Towards Flexible Inference in Sequential Decision Problems via Bidirectional Transformers Micah Carroll Jessy Lin Orr Paradise Raluca Georgescu Mingfei Sun ... Stephanie Milani Katja Hofmann Matthew J. Hausknecht Anca Dragan Sam Devlin OffRL 40 10 0 28 Apr 2022
A Survey of Traversability Estimation for Mobile Robots Christos Sevastopoulos S. Konstantopoulos 46 34 0 22 Apr 2022
Semantic Exploration from Language Abstractions and Pretrained Representations Allison C. Tam Neil C. Rabinowitz Andrew Kyle Lampinen Nicholas A. Roy Stephanie C. Y. Chan D. Strouse Jane X. Wang Andrea Banino Felix Hill LM&Ro 39 67 0 08 Apr 2022
Reinforcement Learning with Action-Free Pre-Training from Videos Younggyo Seo Kimin Lee Stephen James Pieter Abbeel SSL OnRL 18 117 0 25 Mar 2022
Temporal Difference Learning for Model Predictive Control Nicklas Hansen Xiaolong Wang H. Su PINN MU 36 222 0 09 Mar 2022
DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction Masashi Okada T. Taniguchi 3DV OffRL 28 23 0 01 Mar 2022
Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning Chenjia Bai Lingxiao Wang Zhuoran Yang Zhihong Deng Animesh Garg Peng Liu Zhaoran Wang OffRL 31 132 0 23 Feb 2022
TransDreamer: Reinforcement Learning with Transformer World Models Changgu Chen Yi-Fu Wu Jaesik Yoon Sungjin Ahn OffRL 32 90 0 19 Feb 2022
Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach Xuezhou Zhang Yuda Song Masatoshi Uehara Mengdi Wang Alekh Agarwal Wen Sun OffRL 29 57 0 31 Jan 2022
Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning Haichao Zhang Wei-ping Xu Haonan Yu 38 10 0 24 Jan 2022
Physical Derivatives: Computing policy gradients by physical forward-propagation Arash Mehrjou Ashkan Soleymani Stefan Bauer Bernhard Schölkopf 38 0 0 15 Jan 2022
Smooth Model Predictive Path Integral Control without Smoothing Taekyung Kim Gyuhyun Park K. Kwak Jihwan Bae Wonsuk Lee 27 38 0 18 Dec 2021
Model-Value Inconsistency as a Signal for Epistemic Uncertainty Angelos Filos Eszter Vértes Zita Marinho Gregory Farquhar Diana Borsa A. Friesen Feryal M. P. Behbahani Tom Schaul André Barreto Simon Osindero 44 7 0 08 Dec 2021
ED2: Environment Dynamics Decomposition World Models for Continuous Control Jianye Hao Yifu Yuan Cong Wang Zhen Wang OffRL 16 1 0 06 Dec 2021
Learning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Robotics Ingmar Schubert Danny Driess Ozgur S. Oguz Marc Toussaint OffRL 22 1 0 15 Nov 2021
Learning to Cooperate with Unseen Agent via Meta-Reinforcement Learning Rujikorn Charakorn P. Manoonpong Nat Dilokthanakul 33 5 0 05 Nov 2021
Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives Murtaza Dalal Deepak Pathak Ruslan Salakhutdinov 40 90 0 28 Oct 2021
Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching Pierre-Alexandre Kamienny Jean Tarbouriech Sylvain Lamprier A. Lazaric Ludovic Denoyer SSL 40 18 0 27 Oct 2021
OPEn: An Open-ended Physics Environment for Learning Without a Task Chuang Gan Abhishek Bhandwaldar Antonio Torralba J. Tenenbaum Phillip Isola LRM 133 4 0 13 Oct 2021
Neural Algorithmic Reasoners are Implicit Planners Andreea Deac Petar Velivcković Ognjen Milinković Pierre-Luc Bacon Jian Tang Mladen Nikolic OffRL 32 23 0 11 Oct 2021
The Information Geometry of Unsupervised Reinforcement Learning Benjamin Eysenbach Ruslan Salakhutdinov Sergey Levine SSL OffRL 61 31 0 06 Oct 2021
Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks Robert McCarthy Qiang Wang S. Redmond OffRL 27 15 0 05 Oct 2021
Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration Oliver Groth Markus Wulfmeier Giulia Vezzani Vibhavari Dasagi Tim Hertweck Roland Hafner N. Heess Martin Riedmiller LRM 41 20 0 17 Sep 2021
Benchmarking the Spectrum of Agent Capabilities Danijar Hafner ELM 33 127 0 14 Sep 2021
Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain Jianye Hao Tianpei Yang Hongyao Tang Chenjia Bai Jinyi Liu Zhaopeng Meng Peng Liu Zhen Wang OffRL 36 92 0 14 Sep 2021
Backprop-Free Reinforcement Learning with Active Neural Generative Coding Alexander Ororbia A. Mali 41 15 0 10 Jul 2021
Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation Nicklas Hansen H. Su Xiaolong Wang OffRL 26 134 0 01 Jul 2021
Learning to Map for Active Semantic Goal Navigation G. Georgakis Bernadette Bucher Karl Schmeckpeper Siddharth Singh Kostas Daniilidis 32 73 0 29 Jun 2021
Exploration and preference satisfaction trade-off in reward-free learning Noor Sajid P. Tigas Alexey Zakharov Z. Fountas Karl J. Friston 16 20 0 08 Jun 2021
Behavior From the Void: Unsupervised Active Pre-Training Hao Liu Pieter Abbeel VLM SSL 41 195 0 08 Mar 2021
Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design Adam Foster Desi R. Ivanova Ilyas Malik Tom Rainforth 28 78 0 03 Mar 2021
Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning Victor Campos Pablo Sprechmann Steven Hansen André Barreto Steven Kapturowski Alex Vitvitskyi Adria Puigdomenech Badia Charles Blundell OffRL OnRL 38 25 0 24 Feb 2021
Online Safety Assurance for Deep Reinforcement Learning Noga H. Rotman Michael Schapira Aviv Tamar OffRL 36 5 0 07 Oct 2020
Latent World Models For Intrinsically Motivated Exploration Aleksandr Ermolov N. Sebe 25 25 0 05 Oct 2020
Mastering Atari with Discrete World Models Danijar Hafner Timothy Lillicrap Mohammad Norouzi Jimmy Ba DRL 48 814 0 05 Oct 2020
Self-Supervised Policy Adaptation during Deployment Nicklas Hansen Rishabh Jangir Yu Sun Guillem Alenyà Pieter Abbeel Alexei A. Efros Lerrel Pinto Xiaolong Wang 41 159 0 08 Jul 2020
A Unifying Framework for Reinforcement Learning and Planning Thomas M. Moerland Joost Broekens Aske Plaat Catholijn M. Jonker OffRL 33 9 0 26 Jun 2020
Deep Dynamics Models for Learning Dexterous Manipulation Anusha Nagabandi K. Konolige Sergey Levine Vikash Kumar 157 408 0 25 Sep 2019
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles Balaji Lakshminarayanan Alexander Pritzel Charles Blundell UQCV BDL 276 5,675 0 05 Dec 2016