机器人 / 具身智能 - arXivDaily 专题

1910.10754 2019-10-25 cs.LG cs.RO stat.ML 62%

Learning Q-network for Active Information Acquisition

Heejin Jeong, Brent Schlotfeldt, Hamed Hassani, Manfred Morari, Daniel D. Lee, George J. Pappas

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

Comments IROS 2019, Video https://youtu.be/0ZFyOWJ2ulo

Journal ref IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019

1910.09667 2019-10-23 cs.RO cs.LG cs.SY eess.SY 62%

Combining Benefits from Trajectory Optimization and Deep Reinforcement Learning

Guillaume Bellegarda, Katie Byl

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

1910.08811 2019-10-22 cs.CV cs.RO 62%

Active 6D Multi-Object Pose Estimation in Cluttered Scenarios with Deep Reinforcement Learning

Juil Sock, Guillermo Garcia-Hernando, Tae-Kyun Kim

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

1909.12989 2019-10-14 cs.LG cs.RO stat.ME 62%

SURREAL-System: Fully-Integrated Stack for Distributed Deep Reinforcement Learning

Linxi Fan, Yuke Zhu, Jiren Zhu, Zihua Liu, Orien Zeng, Anchit Gupta, Joan Creus-Costa, Silvio Savarese, Li Fei-Fei

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

Comments Technical report of the SURREAL system. See more details at https://surreal.stanford.edu

1907.05634 2019-10-14 cs.LG cs.AI stat.ML 62%

Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling

Yuping Luo, Huazhe Xu, Tengyu Ma

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

1909.13599 2019-10-08 cs.RO cs.AI 62%

End-to-End Motion Planning of Quadrotors Using Deep Reinforcement Learning

Efe Camci, Erdal Kayacan

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

Comments IROS 2019 Workshop, Learning Representations for Planning and Control

1909.12925 2019-10-01 cs.AI cs.LG 62%

Interaction-Aware Multi-Agent Reinforcement Learning for Mobile Agents with Individual Goals

Anahita Mohseni-Kabir, David Isele, Kikuo Fujimura

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

Journal ref ICRA 2019

1909.01500 2019-09-25 cs.LG cs.AI 62%

rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch

Adam Stooke, Pieter Abbeel

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

Comments v2: Updated learning curves for SAC and TD3, improved by bootstrapping value-function when trajectory ends due to time limit, and switching to newer SAC version, now referenced

1909.08052 2019-09-19 cs.HC cs.AI cs.RO 62%

Towards an Adaptive Robot for Sports and Rehabilitation Coaching

Martin K. Ross, Frank Broz, Lynne Baillie

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

Comments AI-HRI 2019

1909.07374 2019-09-18 cs.LG cs.RO stat.ML 62%

A Linearly Constrained Nonparametric Framework for Imitation Learning

Yanlong Huang, Darwin G. Caldwell

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

Comments 7 pages

1906.09090 2019-09-04 cs.LG cs.RO 62%

Entropic Risk Measure in Policy Search

David Nass, Boris Belousov, Jan Peters

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

Comments Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

1908.06973 2019-08-21 cs.LG cs.AI 62%

Reinforcement Learning Applications

Yuxi Li

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

1908.06012 2019-08-19 cs.LG cs.AI stat.ML 62%

Model-based Lookahead Reinforcement Learning

Zhang-Wei Hong, Joni Pajarinen, Jan Peters

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

1908.05546 2019-08-16 cs.RO cs.LG 62%

Sample-efficient Deep Reinforcement Learning with Imaginary Rollouts for Human-Robot Interaction

Mohammad Thabet, Massimiliano Patacchiola, Angelo Cangelosi

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

Comments Accepted for IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019)

1810.06979 2019-08-13 cs.RO cs.HC cs.LG 62%

Learning Socially Appropriate Robot Approaching Behavior Toward Groups using Deep Reinforcement Learning

Yuan Gao, Fangkai Yang, Martin Frisk, Daniel Hernandez, Christopher Peters, Ginevra Castellano

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

Comments accepted for The 28th IEEE International Conference on Robot & Human Interactive Communication (Ro-Man)

1811.11615 2019-07-26 cs.RO cs.LG 62%

Deep Reinforcement Learning for Time Optimal Velocity Control using Prior Knowledge

Gabriel Hartmann, Zvi Shiller, Amos Azaria

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

1807.08364 2019-07-23 cs.LG cs.AI 62%

EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning

Kunal Menda, Katherine Driggs-Campbell, Mykel J. Kochenderfer

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

Comments Accepted to the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019)

1901.03737 2019-07-22 cs.RO cs.LG 62%

Low Level Control of a Quadrotor with Deep Model-Based Reinforcement Learning

Nathan O. Lambert, Daniel S. Drew, Joseph Yaconelli, Roberto Calandra, Sergey Levine, Kristofer S. J. Pister

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

Comments Accepted to IROS and RA-L, 2019. For more information, see the website: https://sites.google.com/berkeley.edu/mbrl-quadrotor/. 9 pages, 12 figures

1905.07866 2019-07-16 cs.RO cs.LG 62%

Reinforcement Learning without Ground-Truth State

Xingyu Lin, Harjatin Singh Baweja, David Held

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

1907.05855 2019-07-15 cs.LG cs.AI stat.ML 62%

DisCoRL: Continual Reinforcement Learning via Policy Distillation

René Traoré, Hugo Caselles-Dupré, Timothée Lesort, Te Sun, Guanghang Cai, Natalia Díaz-Rodríguez, David Filliat

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

Comments arXiv admin note: text overlap with arXiv:1906.04452

1811.02184 2019-07-10 cs.RO cs.LG 62%

Dynamic Regret Convergence Analysis and an Adaptive Regularization Algorithm for On-Policy Robot Imitation Learning

Jonathan N. Lee, Michael Laskey, Ajay Kumar Tanwani, Anil Aswani, Ken Goldberg

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

1906.08928 2019-06-24 cs.RO cs.AI 62%

Learning Reward Functions by Integrating Human Demonstrations and Preferences

Malayandi Palan, Nicholas C. Landolfi, Gleb Shevchuk, Dorsa Sadigh

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

Comments Presented at RSS 2019

1906.05329 2019-06-14 cs.LG cs.AI stat.ML 62%

Sub-Goal Trees -- a Framework for Goal-Directed Trajectory Prediction and Optimization

Tom Jurgenson, Edward Groshev, Aviv Tamar

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

Comments 15 pages (8 main), 2 figures, 4 tables

1906.04452 2019-06-12 cs.LG cs.RO stat.ML 62%

Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer

René Traoré, Hugo Caselles-Dupré, Timothée Lesort, Te Sun, Natalia Díaz-Rodríguez, David Filliat

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

Comments accepted to the Workshop on Multi-Task and Lifelong Reinforcement Learning, ICML 2019

1712.06924 2019-06-11 cs.LG cs.AI stat.ML 62%

Safe Policy Improvement with Baseline Bootstrapping

Romain Laroche, Paul Trichelair, Rémi Tachet des Combes

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

Comments accepted as a long oral at ICML2019

1906.00214 2019-06-04 cs.RO cs.LG stat.ML 62%

Harnessing Reinforcement Learning for Neural Motion Planning

Tom Jurgenson, Aviv Tamar

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

Comments 13 pages (all), 8 pages (main sections), 6 figures, 4 tables, accepted to rss2019

1905.07028 2019-05-20 cs.AI cs.RO cs.SC 62%

A Correctness Result for Synthesizing Plans With Loops in Stochastic Domains

Laszlo Treszkai, Vaishak Belle

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

1905.05731 2019-05-15 cs.LG cs.AI stat.ML 62%

Successor Options: An Option Discovery Framework for Reinforcement Learning

Rahul Ramesh, Manan Tomar, Balaraman Ravindran

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

Comments To appear in the proceedings of the International Joint Conference on Artificial Intelligence 2019 (IJCAI)

1903.01567 2019-03-06 cs.LG cs.AI cs.NE 62%

Model Primitive Hierarchical Lifelong Reinforcement Learning

Bohan Wu, Jayesh K. Gupta, Mykel J. Kochenderfer

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

Comments 9 pages, 10 figures. Accepted as a full paper at AAMAS 2019

Journal ref International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2019)

1902.07015 2019-02-21 cs.LG cs.AI stat.ML 62%

Investigating Generalisation in Continuous Deep Reinforcement Learning

Chenyang Zhao, Olivier Sigaud, Freek Stulp, Timothy M. Hospedales

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

1. 模仿学习与强化学习 4115 篇

Learning Q-network for Active Information Acquisition

Combining Benefits from Trajectory Optimization and Deep Reinforcement Learning

Active 6D Multi-Object Pose Estimation in Cluttered Scenarios with Deep Reinforcement Learning

SURREAL-System: Fully-Integrated Stack for Distributed Deep Reinforcement Learning

Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling

End-to-End Motion Planning of Quadrotors Using Deep Reinforcement Learning

Interaction-Aware Multi-Agent Reinforcement Learning for Mobile Agents with Individual Goals

rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch

Towards an Adaptive Robot for Sports and Rehabilitation Coaching

A Linearly Constrained Nonparametric Framework for Imitation Learning

Entropic Risk Measure in Policy Search

Reinforcement Learning Applications

Model-based Lookahead Reinforcement Learning

Sample-efficient Deep Reinforcement Learning with Imaginary Rollouts for Human-Robot Interaction

Learning Socially Appropriate Robot Approaching Behavior Toward Groups using Deep Reinforcement Learning

Deep Reinforcement Learning for Time Optimal Velocity Control using Prior Knowledge

EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning

Low Level Control of a Quadrotor with Deep Model-Based Reinforcement Learning

Reinforcement Learning without Ground-Truth State

DisCoRL: Continual Reinforcement Learning via Policy Distillation

Dynamic Regret Convergence Analysis and an Adaptive Regularization Algorithm for On-Policy Robot Imitation Learning

Learning Reward Functions by Integrating Human Demonstrations and Preferences

Sub-Goal Trees -- a Framework for Goal-Directed Trajectory Prediction and Optimization

Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer

Safe Policy Improvement with Baseline Bootstrapping

Harnessing Reinforcement Learning for Neural Motion Planning

A Correctness Result for Synthesizing Plans With Loops in Stochastic Domains

Successor Options: An Option Discovery Framework for Reinforcement Learning

Model Primitive Hierarchical Lifelong Reinforcement Learning

Investigating Generalisation in Continuous Deep Reinforcement Learning