机器人 / 具身智能 - arXivDaily 专题

2210.11287 2022-10-21 cs.LG cs.AI cs.RO 75%

MoCoDA: Model-based Counterfactual Data Augmentation

Silviu Pitis, Elliot Creager, Ajay Mandlekar, Animesh Garg

专题命中模仿学习与强化学习：robotics(abstract)；manipulation(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments In Proceedings of NeurIPS 2022. 10 pages (+3 references, +10 appendix). Code available at https://github.com/spitis/mocoda

2210.10899 2022-10-21 cs.RO cs.AI cs.LG stat.ML 75%

Learning Preferences for Interactive Autonomy

Erdem Bıyık

专题命中模仿学习与强化学习：robotics(abstract)；robot learning(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments Ph.D. Thesis (Stanford University), 198 pages

2102.12962 2022-09-27 cs.LG cs.AI cs.RO 75%

Bias-reduced Multi-step Hindsight Experience Replay for Efficient Multi-goal Reinforcement Learning

Rui Yang, Jiafei Lyu, Yu Yang, Jiangpeng Yan, Feng Luo, Dijun Luo, Lanqing Li, Xiu Li

专题命中模仿学习与强化学习：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments 20pages, 8 figures

2207.14299 2022-08-02 cs.LG cs.CV cs.RO 75%

Graph Inverse Reinforcement Learning from Diverse Videos

Sateesh Kumar, Jonathan Zamora, Nicklas Hansen, Rishabh Jangir, Xiaolong Wang

专题命中模仿学习与强化学习：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.CV、cs.LG

Comments Project page: https://sateeshkumar21.github.io/GraphIRL

2112.08932 2022-07-21 cs.LG cs.AI cs.RO 75%

Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning

Trevor Ablett, Bryan Chan, Jonathan Kelly

专题命中模仿学习与强化学习：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments In Proceedings of the Neural Information Processing Systems (NeurIPS'21) Deep Reinforcement Learning Workshop, Sydney, Australia, Dec. 13, 2021

2204.02393 2022-07-19 cs.CV cs.LG cs.RO 75%

Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining

Qihang Zhang, Zhenghao Peng, Bolei Zhou

专题命中模仿学习与强化学习：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.CV、cs.LG

Comments ECCV accepted paper

2207.04136 2022-07-12 cs.LG cs.AI cs.RO 75%

CompoSuite: A Compositional Reinforcement Learning Benchmark

Jorge A. Mendez, Marcel Hussing, Meghna Gummadi, Eric Eaton

专题命中模仿学习与强化学习：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments Published at 1st Conference on Lifelong Learning Agents, 2022; code: https://github.com/Lifelong-ML/CompoSuite

2205.07562 2022-05-17 cs.LG cs.AI cs.RO 75%

Autonomous Open-Ended Learning of Tasks with Non-Stationary Interdependencies

Alejandro Romero, Gianluca Baldassarre, Richard J. Duro, Vieri Giuliano Santucci

专题命中模仿学习与强化学习：robotics(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments Submitted and accepted to "The Multi-disciplinary Conference on Reinforcement Learning and Decision Making" RLDM 2022

2203.05985 2022-03-14 cs.LG cs.CV cs.RO 75%

Graph Neural Networks for Relational Inductive Bias in Vision-based Deep Reinforcement Learning of Robot Control

Marco Oliva, Soubarna Banik, Josip Josifovski, Alois Knoll

专题命中模仿学习与强化学习：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.CV、cs.LG

Comments 8 pages, 7 figures, 1 table. For supplemental material and code, see https://mrcoliva.github.io/relational-inductive-bias-in-vision-based-rl

2107.00644 2021-12-10 cs.LG cs.CV cs.RO 75%

Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation

Nicklas Hansen, Hao Su, Xiaolong Wang

专题命中模仿学习与强化学习：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.CV、cs.LG

Comments Code and videos are available at https://nicklashansen.github.io/SVEA

2107.09996 2021-11-09 cs.RO cs.AI cs.LG 75%

MarsExplorer: Exploration of Unknown Terrains via Deep Reinforcement Learning and Procedurally Generated Environments

Dimitrios I. Koutras, Athanasios Ch. Kapoutsis, Angelos A. Amanatiadis, Elias B. Kosmatopoulos

专题命中模仿学习与强化学习：robotics(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

2110.12985 2021-10-27 cs.LG cs.AI cs.RO 75%

Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning

Kibeom Kim, Min Whoo Lee, Yoonsung Kim, Je-Hwan Ryu, Minsu Lee, Byoung-Tak Zhang

专题命中模仿学习与强化学习：manipulation(abstract)；navigation(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments NeurIPS 2021 accepted, 19 pages including appendix and reference, 8 figures

2109.07788 2021-09-17 cs.RO cs.AI cs.CV 75%

Marginal MAP Estimation for Inverse RL under Occlusion with Observer Noise

Prasanth Sengadu Suresh, Prashant Doshi

专题命中模仿学习与强化学习：robot learning(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.CV

2107.10253 2021-07-22 cs.LG cs.AI cs.RO 75%

Demonstration-Guided Reinforcement Learning with Learned Skills

Karl Pertsch, Youngwoon Lee, Yue Wu, Joseph J. Lim

专题命中模仿学习与强化学习：manipulation(abstract)；navigation(abstract)；分类 cs.RO、cs.AI、cs.LG

2107.06661 2021-07-15 cs.AI cs.LG cs.RO 75%

Plan-Based Relaxed Reward Shaping for Goal-Directed Tasks

Ingmar Schubert, Ozgur S. Oguz, Marc Toussaint

专题命中模仿学习与强化学习：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments Published as a conference paper at ICLR 2021

Journal ref ICLR 2021 - 9th International Conference on Learning Representations

2102.06177 2021-06-14 cs.LG cs.AI cs.RO 75%

Multi-Task Reinforcement Learning with Context-based Representations

Shagun Sodhani, Amy Zhang, Joelle Pineau

专题命中模仿学习与强化学习：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments Accepted at the 38th International Conference on Machine Learning (ICML 2021). 17 pages, 4 figures, 20 tables

2105.14127 2021-06-01 cs.LG cs.AI cs.RO 75%

Risk-Aware Transfer in Reinforcement Learning using Successor Features

Michael Gimelfarb, André Barreto, Scott Sanner, Chi-Guhn Lee

专题命中模仿学习与强化学习：navigation(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

2007.04309 2021-04-12 cs.LG cs.CV cs.RO stat.ML 75%

Self-Supervised Policy Adaptation during Deployment

Nicklas Hansen, Rishabh Jangir, Yu Sun, Guillem Alenyà, Pieter Abbeel, Alexei A. Efros, Lerrel Pinto, Xiaolong Wang

专题命中模仿学习与强化学习：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.CV、cs.LG

Comments Website: https://nicklashansen.github.io/PAD/ Code: https://github.com/nicklashansen/policy-adaptation-during-deployment ICLR 2021

2003.03779 2021-03-18 cs.RO cs.AI cs.LG 75%

Deep Adversarial Reinforcement Learning for Object Disentangling

Melvin Laux, Oleg Arenz, Jan Peters, Joni Pajarinen

专题命中模仿学习与强化学习：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments 7 pages, IROS 2020

1909.11236 2021-01-18 cs.RO cs.AI cs.LG cs.SY eess.SY 75%

Learning to Seek: Autonomous Source Seeking with Deep Reinforcement Learning Onboard a Nano Drone Microcontroller

Bardienus P. Duisterhof, Srivatsan Krishnan, Jonathan J. Cruz, Colby R. Banbury, William Fu, Aleksandra Faust, Guido C. H. E. de Croon, Vijay Janapa Reddi

专题命中模仿学习与强化学习：robot learning(abstract)；navigation(abstract)；分类 cs.RO、cs.AI、cs.LG

2012.11547 2020-12-22 cs.LG cs.AI cs.RO 75%

Offline Reinforcement Learning from Images with Latent Space Models

Rafael Rafailov, Tianhe Yu, Aravind Rajeswaran, Chelsea Finn

专题命中模仿学习与强化学习：robotics(abstract)；manipulation(abstract)；分类 cs.RO、cs.AI、cs.LG

2012.06899 2020-12-15 cs.LG cs.AI cs.RO 75%

Semi-supervised reward learning for offline reinforcement learning

Ksenia Konyushkova, Konrad Zolna, Yusuf Aytar, Alexander Novikov, Scott Reed, Serkan Cabi, Nando de Freitas

专题命中模仿学习与强化学习：robotics(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments Accepted to Offline Reinforcement Learning Workshop at Neural Information Processing Systems (2020)

2003.13661 2020-12-08 cs.LG cs.AI cs.RO stat.ML 75%

Multi-Task Reinforcement Learning with Soft Modularization

Ruihan Yang, Huazhe Xu, Yi Wu, Xiaolong Wang

专题命中模仿学习与强化学习：robotics(abstract)；manipulation(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments Our project page: https://rchalyang.github.io/SoftModule

2011.07213 2020-11-17 cs.RO cs.AI cs.LG 75%

PLAS: Latent Action Space for Offline Reinforcement Learning

Wenxuan Zhou, Sujay Bajracharya, David Held

专题命中模仿学习与强化学习：robotics(abstract)；manipulation(abstract)；分类 cs.RO、cs.AI、cs.LG

1910.01077 2020-11-13 cs.LG cs.AI cs.RO stat.ML 75%

Task-Relevant Adversarial Imitation Learning

Konrad Zolna, Scott Reed, Alexander Novikov, Sergio Gomez Colmenarejo, David Budden, Serkan Cabi, Misha Denil, Nando de Freitas, Ziyu Wang

专题命中模仿学习与强化学习：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments Accepted to CoRL 2020 (see presentation here: https://youtu.be/ZgQvFGuEgFU )

2009.09595 2020-09-22 cs.LG cs.AI cs.RO 75%

RL STaR Platform: Reinforcement Learning for Simulation based Training of Robots

Tamir Blum, Gabin Paillet, Mickael Laine, Kazuya Yoshida

专题命中模仿学习与强化学习：robotics(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments 3 figures, 1 table

2008.04899 2020-08-12 cs.RO cs.CV cs.LG 75%

Visual Imitation Made Easy

Sarah Young, Dhiraj Gandhi, Shubham Tulsiani, Abhinav Gupta, Pieter Abbeel, Lerrel Pinto

专题命中模仿学习与强化学习：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.CV、cs.LG

1907.07500 2020-07-15 cs.RO cs.AI cs.LG 75%

Learning Variable Impedance Control for Contact Sensitive Tasks

Miroslav Bogdanovic, Majid Khadiv, Ludovic Righetti

专题命中模仿学习与强化学习：robotics(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

2006.09641 2020-06-18 cs.LG cs.AI cs.RO stat.ML 75%

Automatic Curriculum Learning through Value Disagreement

Yunzhi Zhang, Pieter Abbeel, Lerrel Pinto

专题命中模仿学习与强化学习：navigation(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments https://sites.google.com/berkeley.edu/vds/

2006.09001 2020-06-17 cs.RO cs.CV cs.LG 75%

RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real

Kanishka Rao, Chris Harris, Alex Irpan, Sergey Levine, Julian Ibarz, Mohi Khansari

专题命中模仿学习与强化学习：robotics(abstract)；robotic(abstract)；分类 cs.RO、cs.CV、cs.LG

Comments Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020)

1. 模仿学习与强化学习 4118 篇

MoCoDA: Model-based Counterfactual Data Augmentation

Learning Preferences for Interactive Autonomy

Bias-reduced Multi-step Hindsight Experience Replay for Efficient Multi-goal Reinforcement Learning

Graph Inverse Reinforcement Learning from Diverse Videos

Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning

Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining

CompoSuite: A Compositional Reinforcement Learning Benchmark

Autonomous Open-Ended Learning of Tasks with Non-Stationary Interdependencies

Graph Neural Networks for Relational Inductive Bias in Vision-based Deep Reinforcement Learning of Robot Control

Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation

MarsExplorer: Exploration of Unknown Terrains via Deep Reinforcement Learning and Procedurally Generated Environments

Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning

Marginal MAP Estimation for Inverse RL under Occlusion with Observer Noise

Demonstration-Guided Reinforcement Learning with Learned Skills

Plan-Based Relaxed Reward Shaping for Goal-Directed Tasks

Multi-Task Reinforcement Learning with Context-based Representations

Risk-Aware Transfer in Reinforcement Learning using Successor Features

Self-Supervised Policy Adaptation during Deployment

Deep Adversarial Reinforcement Learning for Object Disentangling

Learning to Seek: Autonomous Source Seeking with Deep Reinforcement Learning Onboard a Nano Drone Microcontroller

Offline Reinforcement Learning from Images with Latent Space Models

Semi-supervised reward learning for offline reinforcement learning

Multi-Task Reinforcement Learning with Soft Modularization

PLAS: Latent Action Space for Offline Reinforcement Learning

Task-Relevant Adversarial Imitation Learning

RL STaR Platform: Reinforcement Learning for Simulation based Training of Robots

Visual Imitation Made Easy

Learning Variable Impedance Control for Contact Sensitive Tasks

Automatic Curriculum Learning through Value Disagreement

RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real