机器人 / 具身智能 - arXivDaily 专题

2004.04574 2021-04-22 cs.AI cs.LG 73%

Model-based actor-critic: GAN (model generator) + DRL (actor-critic) => AGI

Aras Dargazany

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

Comments arXiv admin note: text overlap with arXiv:1610.01945, arXiv:1903.04411, arXiv:1910.01007 by other authors

2103.15793 2021-03-31 cs.RO cs.AI 73%

LASER: Learning a Latent Action Space for Efficient Reinforcement Learning

Arthur Allshire, Roberto Martín-Martín, Charles Lin, Shawn Manuel, Silvio Savarese, Animesh Garg

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

Comments Accepted as a conference paper at ICRA 2021. 7 pages, 8 figures

2007.14535 2021-03-15 cs.LG cs.AI cs.SY eess.SY stat.ML 73%

Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction

Masashi Okada, Tadahiro Taniguchi

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

Comments Accepted to ICRA2021. Camera ready version

2103.05349 2021-03-10 cs.RO cs.AI 73%

I am Robot: Neuromuscular Reinforcement Learning to Actuate Human Limbs through Functional Electrical Stimulation

Nat Wannawas, Ali Shafti, A. Aldo Faisal

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

2011.11270 2020-11-24 cs.RO cs.LG 73%

COCOI: Contact-aware Online Context Inference for Generalizable Non-planar Pushing

Zhuo Xu, Wenhao Yu, Alexander Herzog, Wenlong Lu, Chuyuan Fu, Masayoshi Tomizuka, Yunfei Bai, C. Karen Liu, Daniel Ho

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

2011.10024 2020-11-20 cs.LG cs.RO 73%

Parrot: Data-Driven Behavioral Priors for Reinforcement Learning

Avi Singh, Huihan Liu, Gaoyue Zhou, Albert Yu, Nicholas Rhinehart, Sergey Levine

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

Comments First two authors contributed equally. Project website: https://sites.google.com/view/parrot-rl

2010.14603 2020-10-29 cs.LG cs.RO 73%

Learning to be Safe: Deep RL with a Safety Critic

Krishnan Srinivasan, Benjamin Eysenbach, Sehoon Ha, Jie Tan, Chelsea Finn

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

Comments In submission, 16 pages (including appendix)

2010.14500 2020-10-28 cs.LG cs.RO 73%

COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning

Avi Singh, Albert Yu, Jonathan Yang, Jesse Zhang, Aviral Kumar, Sergey Levine

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

Comments Accepted to CoRL 2020. Source code and videos available at https://sites.google.com/view/cog-rl

1902.06007 2020-09-25 cs.LG cs.AI stat.ML 73%

Neural-encoding Human Experts' Domain Knowledge to Warm Start Reinforcement Learning

Andrew Silva, Matthew Gombolay

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

2007.03363 2020-09-22 cs.AI cs.MA cs.RO 73%

Deep Reinforcement Learning with Interactive Feedback in a Human-Robot Environment

Ithan Moreira, Javier Rivas, Francisco Cruz, Richard Dazeley, Angel Ayala, Bruno Fernandes

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

Comments In press journal Applied Sciences

2008.00614 2020-08-04 cs.LG cs.AI stat.ML 73%

Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning

Xingyu Lu, Kimin Lee, Pieter Abbeel, Stas Tiomkin

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

Comments 16 pages

2003.05117 2020-07-28 cs.RO cs.AI 73%

Multiplicative Controller Fusion: Leveraging Algorithmic Priors for Sample-efficient Reinforcement Learning and Safe Sim-To-Real Transfer

Krishan Rana, Vibhavari Dasagi, Ben Talbot, Michael Milford, Niko Sünderhauf

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

Comments Accepted for presentation at IROS2020. Project site available at https://sites.google.com/view/mcf-nav/home

1909.04134 2020-07-06 cs.LG cs.AI stat.ML 73%

Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning

Arjun Manoharan, Rahul Ramesh, Balaraman Ravindran

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

Comments ECML-PKDD 2020

2006.03647 2020-06-24 cs.LG cs.AI stat.ML 73%

Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization

Tatsuya Matsushima, Hiroki Furuta, Yutaka Matsuo, Ofir Nachum, Shixiang Gu

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

1902.08039 2020-05-27 cs.LG cs.AI stat.ML 73%

Curiosity-Driven Experience Prioritization via Density Estimation

Rui Zhao, Volker Tresp

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

Comments Accepted by NIPS Deep RL Workshop, 2018, link: https://sites.google.com/view/deep-rl-workshop-nips-2018 . arXiv admin note: substantial text overlap with arXiv:1810.01363 and text overlap with arXiv:1905.08786

2005.09476 2020-05-20 cs.RO cs.LG 73%

Learning to Herd Agents Amongst Obstacles: Training Robust Shepherding Behaviors using Deep Reinforcement Learning

Jixuan Zhi, Jyh-Ming Lien

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

2003.02634 2020-03-06 cs.RO cs.LG stat.ML 73%

Dimensionality Reduction of Movement Primitives in Parameter Space

Samuele Tosatto, Jonas Stadtmueller, Jan Peters

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

1906.01408 2020-03-04 cs.LG cs.AI stat.ML 73%

Hypothesis-Driven Skill Discovery for Hierarchical Deep Reinforcement Learning

Caleb Chuck, Supawit Chockchowwat, Scott Niekum

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

Comments Submitted to IROS 2020

2002.10126 2020-02-25 cs.RO cs.AI cs.SY eess.SY 73%

Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach

Subin Huh, Insoon Yang

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

2002.09136 2020-02-24 cs.LG cs.CV stat.ML 73%

Disentangling Controllable Object through Video Prediction Improves Visual Reinforcement Learning

Yuanyi Zhong, Alexander Schwing, Jian Peng

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

Comments Accepted to ICASSP 2020

2001.08092 2020-01-23 cs.LG cs.RO cs.SY eess.SY stat.ML 73%

Local Policy Optimization for Trajectory-Centric Reinforcement Learning

Patrik Kolaric, Devesh K. Jha, Arvind U. Raghunathan, Frank L. Lewis, Mouhacine Benosman, Diego Romeres, Daniel Nikovski

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

Journal ref ICRA 2020

1912.13037 2020-01-01 cs.LG cs.AI stat.ML 73%

A New Framework for Query Efficient Active Imitation Learning

Daniel Hsu

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

1909.10618 2020-01-01 cs.LG cs.AI stat.ML 73%

Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?

Ofir Nachum, Haoran Tang, Xingyu Lu, Shixiang Gu, Honglak Lee, Sergey Levine

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

Comments Presented as an oral at the NeurIPS 2019 DeepRL Workshop

1912.04226 2019-12-10 cs.AI cs.LG 73%

Unsupervised Curricula for Visual Meta-Reinforcement Learning

Allan Jabri, Kyle Hsu, Ben Eysenbach, Abhishek Gupta, Sergey Levine, Chelsea Finn

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

Comments NeurIPS 2019

1811.03307 2019-11-20 cs.RO cs.LG 73%

Memory-based Deep Reinforcement Learning for Obstacle Avoidance in UAV with Limited Environment Knowledge

Abhik Singla, Sindhu Padakandla, Shalabh Bhatnagar

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

Comments Submitted to IEEE Transactions on Cybernetics. Supplementary Video: https://www.youtube.com/watch?v=Lqh_B9U3Gv0

1910.11956 2019-10-29 cs.LG cs.RO stat.ML 73%

Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning

Abhishek Gupta, Vikash Kumar, Corey Lynch, Sergey Levine, Karol Hausman

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

Comments Published at CoRL 2019

1910.03732 2019-10-10 cs.LG cs.RO stat.ML 73%

Ctrl-Z: Recovering from Instability in Reinforcement Learning

Vibhavari Dasagi, Jake Bruce, Thierry Peynot, Jürgen Leitner

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

Comments Submitted to ICRA2020, under review

1906.07805 2019-06-20 cs.LG cs.AI stat.ML 73%

Directed Exploration for Reinforcement Learning

Zhaohan Daniel Guo, Emma Brunskill

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

1811.07882 2019-01-30 cs.LG cs.AI cs.CL cs.HC 73%

Guiding Policies with Language via Meta-Learning

John D. Co-Reyes, Abhishek Gupta, Suvansh Sanjeev, Nick Altieri, Jacob Andreas, John DeNero, Pieter Abbeel, Sergey Levine

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

Comments Accepted at ICLR 2019

1809.02070 2018-09-10 cs.LG cs.AI stat.ML 73%

ARCHER: Aggressive Rewards to Counter bias in Hindsight Experience Replay

Sameera Lanka, Tianfu Wu

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

Comments 8 pages

1. 模仿学习与强化学习 4111 篇

Model-based actor-critic: GAN (model generator) + DRL (actor-critic) => AGI

LASER: Learning a Latent Action Space for Efficient Reinforcement Learning

Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction

I am Robot: Neuromuscular Reinforcement Learning to Actuate Human Limbs through Functional Electrical Stimulation

COCOI: Contact-aware Online Context Inference for Generalizable Non-planar Pushing

Parrot: Data-Driven Behavioral Priors for Reinforcement Learning

Learning to be Safe: Deep RL with a Safety Critic

COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning

Neural-encoding Human Experts' Domain Knowledge to Warm Start Reinforcement Learning

Deep Reinforcement Learning with Interactive Feedback in a Human-Robot Environment

Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning

Multiplicative Controller Fusion: Leveraging Algorithmic Priors for Sample-efficient Reinforcement Learning and Safe Sim-To-Real Transfer

Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning

Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization

Curiosity-Driven Experience Prioritization via Density Estimation

Learning to Herd Agents Amongst Obstacles: Training Robust Shepherding Behaviors using Deep Reinforcement Learning

Dimensionality Reduction of Movement Primitives in Parameter Space

Hypothesis-Driven Skill Discovery for Hierarchical Deep Reinforcement Learning

Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach

Disentangling Controllable Object through Video Prediction Improves Visual Reinforcement Learning

Local Policy Optimization for Trajectory-Centric Reinforcement Learning

A New Framework for Query Efficient Active Imitation Learning

Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?

Unsupervised Curricula for Visual Meta-Reinforcement Learning

Memory-based Deep Reinforcement Learning for Obstacle Avoidance in UAV with Limited Environment Knowledge

Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning

Ctrl-Z: Recovering from Instability in Reinforcement Learning

Directed Exploration for Reinforcement Learning

Guiding Policies with Language via Meta-Learning

ARCHER: Aggressive Rewards to Counter bias in Hindsight Experience Replay