机器人 / 具身智能 - arXivDaily 专题

2103.02142 2021-07-27 cs.RO cs.LG 62%

Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control

Jacopo Panerati, Hehui Zheng, SiQi Zhou, James Xu, Amanda Prorok, Angela P. Schoellig

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

Comments 8 pages, 11 figures, accepted for presentation at IROS 2021

2104.00053 2021-07-22 cs.RO cs.AI 62%

LazyDAgger: Reducing Context Switching in Interactive Imitation Learning

Ryan Hoque, Ashwin Balakrishna, Carl Putterman, Michael Luo, Daniel S. Brown, Daniel Seita, Brijen Thananjeyan, Ellen Novoseller, Ken Goldberg

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

Comments IEEE CASE 2021

2107.09359 2021-07-21 cs.LG cs.AI 62%

An Empirical Analysis of Measure-Valued Derivatives for Policy Gradients

João Carvalho, Davide Tateo, Fabio Muratore, Jan Peters

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

2107.08577 2021-07-20 cs.LG cs.AI 62%

Structured World Belief for Reinforcement Learning in POMDP

Gautam Singh, Skand Peri, Junghyun Kim, Hyunseok Kim, Sungjin Ahn

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

Comments Published in ICML 2021

2107.08398 2021-07-20 cs.AI cs.LG 62%

Unsupervised Skill-Discovery and Skill-Learning in Minecraft

Juan José Nieto, Roger Creus, Xavier Giro-i-Nieto

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

Comments Accepted at ICML Unsupervised RL Workshop, 8 pages

2107.08241 2021-07-20 cs.LG cs.AI 62%

High-Accuracy Model-Based Reinforcement Learning, a Survey

Aske Plaat, Walter Kosters, Mike Preuss

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

Comments arXiv admin note: text overlap with arXiv:2008.05598

2107.04538 2021-07-12 cs.RO cs.AI 62%

Learning Interaction-aware Guidance Policies for Motion Planning in Dense Traffic Scenarios

Bruno Brito, Achin Agarwal, Javier Alonso-Mora

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

2107.04527 2021-07-12 cs.RO cs.LG 62%

BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with IsaacGym

Rika Antonova, Fabio Ramos, Rafael Possas, Dieter Fox

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

2106.13911 2021-06-29 cs.LG cs.AI 62%

Predictive Control Using Learned State Space Models via Rolling Horizon Evolution

Alvaro Ovalle, Simon M. Lucas

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

Comments Accepted at the Bridging the Gap Between AI Planning and Reinforcement Learning (PRL) Workshop at ICAPS 2021

2106.13105 2021-06-25 cs.AI cs.LG 62%

The Option Keyboard: Combining Skills in Reinforcement Learning

André Barreto, Diana Borsa, Shaobo Hou, Gheorghe Comanici, Eser Aygün, Philippe Hamel, Daniel Toyama, Jonathan Hunt, Shibl Mourad, David Silver, Doina Precup

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

Comments Published at NeurIPS 2019

2106.11365 2021-06-23 cs.RO cs.AI cs.MA 62%

Distributed Heuristic Multi-Agent Path Finding with Communication

Ziyuan Ma, Yudong Luo, Hang Ma

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

Comments Published at ICRA 2021

2106.07892 2021-06-16 cs.RO cs.AI cs.MA 62%

Towards Safe Control of Continuum Manipulator Using Shielded Multiagent Reinforcement Learning

Guanglin Ji, Junyan Yan, Jingxin Du, Wanquan Yan, Jibiao Chen, Yongkang Lu, Juan Rojas, Shing Shin Cheng

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

Comments 8 pages, 12 figs, 1 table, 2 pseudo-code

2010.14771 2021-06-09 cs.LG cs.AI 62%

Batch Reinforcement Learning with a Nonparametric Off-Policy Policy Gradient

Samuele Tosatto, João Carvalho, Jan Peters

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

Comments arXiv admin note: substantial text overlap with arXiv:2001.02435

2105.03019 2021-06-08 cs.RO cs.LG 62%

Imitation Learning via Simultaneous Optimization of Policies and Auxiliary Trajectories

Mandy Xie, Anqi Li, Karl Van Wyk, Frank Dellaert, Byron Boots, Nathan Ratliff

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

2102.11448 2021-06-07 cs.LG cs.AI 62%

MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning

DiJia Su, Jason D. Lee, John M. Mulvey, H. Vincent Poor

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

2005.10619 2021-06-03 cs.LG cs.AI stat.ML 62%

A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environments

Sindhu Padakandla

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

Journal ref ACM Computing Surveys 2021

2105.14471 2021-06-01 cs.AI cs.RO 62%

Reducing the Deployment-Time Inference Control Costs of Deep Reinforcement Learning Agents via an Asymmetric Architecture

Chin-Jui Chang, Yu-Wei Chu, Chao-Hsien Ting, Hao-Kang Liu, Zhang-Wei Hong, Chun-Yi Lee

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

2105.13806 2021-05-31 cs.RO cs.AI 62%

DRL: Deep Reinforcement Learning for Intelligent Robot Control -- Concept, Literature, and Future

Aras Dargazany

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

2103.05196 2021-05-31 cs.LG cs.AI 62%

A Learning-Based Computational Impact Time Guidance

Zichao Liu, Jiang Wang, Shaoming He, Hyo-Sang Shin, Antonios Tsourdos

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

2105.08710 2021-05-20 cs.LG cs.AI 62%

Fast and Slow Learning of Recurrent Independent Mechanisms

Kanika Madan, Nan Rosemary Ke, Anirudh Goyal, Bernhard Schölkopf, Yoshua Bengio

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

Comments Accepted at ICLR'21

2105.04699 2021-05-12 cs.LG cs.AI 62%

Adaptive Policy Transfer in Reinforcement Learning

Girish Joshi, Girish Chowdhary

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

2005.04536 2021-05-10 cs.NE cs.AI cs.AR cs.DC cs.LG 62%

Accelerating Deep Neuroevolution on Distributed FPGAs for Reinforcement Learning Problems

Alexis Asseman, Nicolas Antoine, Ahmet S. Ozcan

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

Comments 12 pages. Submitted to ACM Journal on Emerging Technologies in Computing Systems: Special Issue on Hardware and Algorithms for Efficient Machine Learning

2006.11419 2021-05-07 cs.LG cs.AI stat.ML 62%

FISAR: Forward Invariant Safe Reinforcement Learning with a Deep Neural Network-Based Optimize

Chuangchuang Sun, Dong-Ki Kim, Jonathan P. How

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

Comments Accepted to ICML 2020 Workshop Theoretical Foundations of RL; Accepted to ICRA 2021

2105.01620 2021-05-06 cs.LG cs.AI 62%

Data-Efficient Reinforcement Learning for Malaria Control

Lixin Zou, Long Xia, Linfang Hou, Xiangyu Zhao, Dawei Yin

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

Comments 7 pages, 4 figures, IJCAI 2021 Accepted Paper

2105.00153 2021-05-04 cs.RO cs.LG 62%

Pedestrian Collision Avoidance for Autonomous Vehicles at Unsignalized Intersection Using Deep Q-Network

Kasra Mokhtari, Alan R. Wagner

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

Comments 8 pages, 8 figures, 6 tables

1911.10635 2021-04-30 cs.LG cs.AI cs.MA stat.ML 62%

Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms

Kaiqing Zhang, Zhuoran Yang, Tamer Başar

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

Comments Invited Chapter in Handbook on RL and Control (Springer Studies in Systems, Decision and Control); Proofread version from the Publisher

2104.08492 2021-04-20 cs.AI cs.LG 62%

A Self-Supervised Auxiliary Loss for Deep RL in Partially Observable Settings

Eltayeb Ahmed, Luisa Zintgraf, Christian A. Schroeder de Witt, Nicolas Usunier

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

2104.02921 2021-04-20 cs.RO cs.CV 62%

Unsupervised Visual Attention and Invariance for Reinforcement Learning

Xudong Wang, Long Lian, Stella X. Yu

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

Comments Accepted at CVPR 2021

2012.05909 2021-04-15 cs.LG cs.RO 62%

Blending MPC & Value Function Approximation for Efficient Reinforcement Learning

Mohak Bhardwaj, Sanjiban Choudhury, Byron Boots

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

Comments 15 pages

Journal ref International Conference on Learning Representations (ICLR), 2021

2011.08345 2021-04-07 cs.LG cs.RO 62%

Distilling a Hierarchical Policy for Planning and Control via Representation and Reinforcement Learning

Jung-Su Ha, Young-Jin Park, Hyeok-Joo Chae, Soon-Seo Park, Han-Lim Choi

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

Comments ICRA 2021, the first two authors contributed equally

1. 模仿学习与强化学习 4115 篇

Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control

LazyDAgger: Reducing Context Switching in Interactive Imitation Learning

An Empirical Analysis of Measure-Valued Derivatives for Policy Gradients

Structured World Belief for Reinforcement Learning in POMDP

Unsupervised Skill-Discovery and Skill-Learning in Minecraft

High-Accuracy Model-Based Reinforcement Learning, a Survey

Learning Interaction-aware Guidance Policies for Motion Planning in Dense Traffic Scenarios

BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with IsaacGym

Predictive Control Using Learned State Space Models via Rolling Horizon Evolution

The Option Keyboard: Combining Skills in Reinforcement Learning

Distributed Heuristic Multi-Agent Path Finding with Communication

Towards Safe Control of Continuum Manipulator Using Shielded Multiagent Reinforcement Learning

Batch Reinforcement Learning with a Nonparametric Off-Policy Policy Gradient

Imitation Learning via Simultaneous Optimization of Policies and Auxiliary Trajectories

MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning

A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environments

Reducing the Deployment-Time Inference Control Costs of Deep Reinforcement Learning Agents via an Asymmetric Architecture

DRL: Deep Reinforcement Learning for Intelligent Robot Control -- Concept, Literature, and Future

A Learning-Based Computational Impact Time Guidance

Fast and Slow Learning of Recurrent Independent Mechanisms

Adaptive Policy Transfer in Reinforcement Learning

Accelerating Deep Neuroevolution on Distributed FPGAs for Reinforcement Learning Problems

FISAR: Forward Invariant Safe Reinforcement Learning with a Deep Neural Network-Based Optimize

Data-Efficient Reinforcement Learning for Malaria Control

Pedestrian Collision Avoidance for Autonomous Vehicles at Unsignalized Intersection Using Deep Q-Network

Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms

A Self-Supervised Auxiliary Loss for Deep RL in Partially Observable Settings

Unsupervised Visual Attention and Invariance for Reinforcement Learning

Blending MPC & Value Function Approximation for Efficient Reinforcement Learning

Distilling a Hierarchical Policy for Planning and Control via Representation and Reinforcement Learning