Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels

28 April 2020

Papers citing "Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels"

50 / 183 papers shown

Title
Contrastive Learning as Goal-Conditioned Reinforcement Learning Benjamin Eysenbach Tianjun Zhang Ruslan Salakhutdinov Sergey Levine SSL OffRL 25 138 0 15 Jun 2022
Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels? Xiang Li Jinghuan Shang Srijan Das Michael S. Ryoo SSL 27 31 0 10 Jun 2022
Consensus Learning for Cooperative Multi-Agent Reinforcement Learning Zhiwei Xu Bin Zhang Dapeng Li Zeren Zhang Guangchong Zhou Hao Chen Guoliang Fan 16 14 0 06 Jun 2022
Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress Rishabh Agarwal Max Schwarzer P. S. Castro Aaron C. Courville Marc G. Bellemare OffRL OnRL 26 64 0 03 Jun 2022
BulletArm: An Open-Source Robotic Manipulation Benchmark and Learning Framework Dian Wang Colin Kohler Xu Zhu Ming Jia Robert W. Platt 27 9 0 28 May 2022
Nuclear Norm Maximization Based Curiosity-Driven Learning Chao Chen Zijian Gao Kele Xu Sen Yang Yiying Li Bo Ding Dawei Feng Huaimin Wang 131 5 0 21 May 2022
Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions Rui Yang Jie Wang Zijie Geng Mingxuan Ye Shuiwang Ji Bin Li Fengli Wu OOD 31 20 0 20 May 2022
Image Augmentation Based Momentum Memory Intrinsic Reward for Sparse Reward Visual Scenes Zheng Fang Biao Zhao Guizhong Liu 16 2 0 19 May 2022
Neighborhood Mixup Experience Replay: Local Convex Interpolation for Improved Sample Efficiency in Continuous Control Tasks Ryan M Sander Wilko Schwarting Tim Seyde Igor Gilitschenski S. Karaman Daniela Rus 33 2 0 18 May 2022
The Primacy Bias in Deep Reinforcement Learning Evgenii Nikishin Max Schwarzer P. DÓro Pierre-Luc Bacon Aaron C. Courville OnRL 93 180 0 16 May 2022
Identical Image Retrieval using Deep Learning Sayan Nath Nikhil Nayak VLM 34 1 0 10 May 2022
CCLF: A Contrastive-Curiosity-Driven Learning Framework for Sample-Efficient Reinforcement Learning Chenyu Sun Hangwei Qian C. Miao OffRL 24 12 0 02 May 2022
Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning Philippe Hansen-Estruch Amy Zhang Ashvin Nair Patrick Yin Sergey Levine AI4CE 23 27 0 27 Apr 2022
Local Feature Swapping for Generalization in Reinforcement Learning David Bertoin Emmanuel Rachelson OOD 21 14 0 13 Apr 2022
Evaluating Vision Transformer Methods for Deep Reinforcement Learning from Pixels Tianxin Tao Daniele Reda M. van de Panne ViT 11 19 0 11 Apr 2022
Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining Qihang Zhang Zhenghao Peng Bolei Zhou SSL 22 37 0 05 Apr 2022
Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots Yufeng Yuan Rupam Mahmood OffRL 20 18 0 23 Mar 2022
Review of Metrics to Measure the Stability, Robustness and Resilience of Reinforcement Learning L. Pullum 11 2 0 22 Mar 2022
Vision-Based Manipulators Need to Also See from Their Hands Kyle Hsu Moo Jin Kim Rafael Rafailov Jiajun Wu Chelsea Finn 24 44 0 15 Mar 2022
Temporal Difference Learning for Model Predictive Control Nicklas Hansen Xiaolong Wang H. Su PINN MU 36 220 0 09 Mar 2022
On-Robot Learning With Equivariant Models Dian Wang Ming Jia Xu Zhu Robin G. Walters Robert W. Platt OffRL SSL 28 35 0 09 Mar 2022
$$\mathrm{SO}(2)$-Equivariant Reinforcement Learning$ $\mathrm{SO}(2)$ -Equivariant Reinforcement Learning Dian Wang Robin G. Walters Robert W. Platt 30 78 0 08 Mar 2022
The Unsurprising Effectiveness of Pre-Trained Vision Models for Control Simone Parisi Aravind Rajeswaran Senthil Purushwalkam Abhinav Gupta LM&Ro 28 186 0 07 Mar 2022
Fast and Data Efficient Reinforcement Learning from Pixels via Non-Parametric Value Approximation Alex Long Alan Blair H. V. Hoof 23 3 0 07 Mar 2022
Evolving Curricula with Regret-Based Environment Design Jack Parker-Holder Minqi Jiang Michael Dennis Mikayel Samvelyan Jakob N. Foerster Edward Grefenstette Tim Rocktaschel 31 116 0 02 Mar 2022
Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning Zhecheng Yuan Guozheng Ma Yao Mu Bo Xia Bo Yuan Xueqian Wang Ping Luo Huazhe Xu 25 28 0 21 Feb 2022
Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation Rishabh Jangir Nicklas Hansen Sambaran Ghosal Mohit Jain Xiaolong Wang 24 65 0 19 Jan 2022
Accelerating Representation Learning with View-Consistent Dynamics in Data-Efficient Reinforcement Learning Tao Huang Jiacheng Wang Xiao Chen 34 4 0 18 Jan 2022
Task-Oriented Image Transmission for Scene Classification in Unmanned Aerial Systems Xu Kang Bin Song Jie Guo Zhijin Qin F. Yu 12 95 0 21 Dec 2021
Symmetry-aware Neural Architecture for Embodied Visual Navigation Shuang Liu Takayuki Okatani 34 1 0 17 Dec 2021
Residual Pathway Priors for Soft Equivariance Constraints Marc Finzi Gregory W. Benton A. Wilson BDL UQCV 24 50 0 02 Dec 2021
Learning State Representations via Retracing in Reinforcement Learning Changmin Yu Dong Li Jianye Hao Jun Wang Neil Burgess 22 7 0 24 Nov 2021
B-Pref: Benchmarking Preference-Based Reinforcement Learning Kimin Lee Laura M. Smith Anca Dragan Pieter Abbeel OffRL 27 93 0 04 Nov 2021
Mastering Atari Games with Limited Data Weirui Ye Shao-Wei Liu Thanard Kurutach Pieter Abbeel Yang Gao VLM 40 222 0 30 Oct 2021
Equivariant $Q$ Learning in Spatial Action Spaces Dian Wang Robin G. Walters Xu Zhu Robert W. Platt 27 72 0 28 Oct 2021
DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations Fei Deng Ingook Jang Sungjin Ahn VLM 29 62 0 27 Oct 2021
Learning Domain Invariant Representations in Goal-conditioned Block MDPs Beining Han Chongyi Zheng Harris Chan Keiran Paster Michael Ruogu Zhang Jimmy Ba OOD AI4CE 20 13 0 27 Oct 2021
Efficient Robotic Manipulation Through Offline-to-Online Reinforcement Learning and Goal-Aware State Information Jin Li Xianyuan Zhan Zixu Xiao Guyue Zhou OffRL OnRL 27 2 0 21 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
Multi-Agent MDP Homomorphic Networks Elise van der Pol H. V. Hoof F. Oliehoek Max Welling AI4CE 46 28 0 09 Oct 2021
Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning Edoardo Cetin Oya Celiktutan OffRL 39 16 0 07 Oct 2021
Reinforcement Learning on Encrypted Data Alberto Jesu Victor-Alexandru Darvariu Alessandro Staffolani R. Montanari Mirco Musolesi OffRL 16 1 0 16 Sep 2021
Robust Predictable Control Benjamin Eysenbach Ruslan Salakhutdinov Sergey Levine OffRL 24 44 0 07 Sep 2021
APS: Active Pretraining with Successor Features Hao Liu Pieter Abbeel 31 118 0 31 Aug 2021
A review of mobile robot motion planning methods: from classical motion planning workflows to reinforcement learning-based architectures Jiawei Wang Zicheng He Chunwei Song Changyin Sun 33 54 0 31 Aug 2021
Deep Reinforcement Learning at the Edge of the Statistical Precipice Rishabh Agarwal Max Schwarzer P. S. Castro Aaron Courville Marc G. Bellemare OffRL 41 633 0 30 Aug 2021
Active Reinforcement Learning over MDPs Qi Yang Peng Yang K. Tang 33 0 0 05 Aug 2021
Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning Denis Yarats Rob Fergus A. Lazaric Lerrel Pinto OffRL 11 337 0 20 Jul 2021
Visual Adversarial Imitation Learning using Variational Models Rafael Rafailov Tianhe Yu Aravind Rajeswaran Chelsea Finn SSL 28 49 0 16 Jul 2021
Distributionally Robust Policy Learning via Adversarial Environment Generation Allen Z. Ren Anirudha Majumdar OOD 96 15 0 13 Jul 2021