机器人 / 具身智能 - arXivDaily 专题

2306.05582 2023-06-12 cs.AI q-bio.NC 57%

A newborn embodied Turing test for view-invariant object recognition

Denizhan Pak, Donsuk Lee, Samantha M. W. Wood, Justin N. Wood

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

Comments 7 Pages. 4 figures, 1 table. This paper was accepted to the CogSci 2023 Conference. (https://cognitivesciencesociety.org/)

2207.10415 2023-06-06 math.OC cs.LG 57%

Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning

Ilnura Usmanova, Yarden As, Maryam Kamgarpour, Andreas Krause

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

Comments 36 pages, 9 pages of appendix

2202.02006 2023-05-29 cs.NI cs.AI 57%

5G Network on Wings: A Deep Reinforcement Learning Approach to the UAV-based Integrated Access and Backhaul

Hongyi Zhang, Zhiqiang Qi, Jingya Li, Anders Aronsson, Jan Bosch, Helena Holmström Olsson

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

2305.14586 2023-05-25 cs.RO 57%

MARC: A multi-agent robots control framework for enhancing reinforcement learning in construction tasks

Kangkang Duan, Christine Wun Ki Suen, Zhengbo Zou

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

Comments 19 pages

2302.12600 2023-05-23 cs.NE cs.AI 57%

EvoTorch: Scalable Evolutionary Computation in Python

Nihat Engin Toklu, Timothy Atkinson, Vojtěch Micka, Paweł Liskowski, Rupesh Kumar Srivastava

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

2305.11358 2023-05-22 cs.LG cs.MA 57%

Understanding the World to Solve Social Dilemmas Using Multi-Agent Reinforcement Learning

Manuel Rios, Nicanor Quijano, Luis Felipe Giraldo

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

Comments ICLR 2023 - AI4ABM workshop

2304.03326 2023-05-19 math.OC cs.RO cs.SY eess.SY math.DS nlin.CD 57%

Finite Time Lyapunov Exponent Analysis of Model Predictive Control and Reinforcement Learning

Kartik Krishna, Steven L. Brunton, Zhuoyuan Song

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

Comments 22 pages, 12 figures

2205.14495 2023-05-19 cs.LG 57%

Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges

Massimo Caccia, Jonas Mueller, Taesup Kim, Laurent Charlin, Rasool Fakoor

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

Journal ref CoLLAs 2023

2109.06831 2023-05-16 cs.RO 57%

Multi-Agent Deep Reinforcement Learning For Persistent Monitoring With Sensing, Communication, and Localization Constraints

Manav Mishra, Prithvi Poddar, Rajat Agarwal, Jingxi Chen, Pratap Tokekar, P. B. Sujit

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

2206.02678 2023-05-12 cs.LG 57%

Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path

Yihan Du, Siwei Wang, Longbo Huang

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

2305.03870 2023-05-11 cs.LG 57%

Knowledge Transfer from Teachers to Learners in Growing-Batch Reinforcement Learning

Patrick Emedom-Nnamdi, Abram L. Friesen, Bobak Shahriari, Nando de Freitas, Matt W. Hoffman

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

Comments Reincarnating Reinforcement Learning Workshop at ICLR 2023

2303.01618 2023-05-09 cs.AI 57%

Deconstructing deep active inference

Théophile Champion, Marek Grześ, Lisa Bonheme, Howard Bowman

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

Comments 59 pages, 46 figures

2203.15955 2023-05-08 cs.LG 57%

Investigating the Properties of Neural Network Representations in Reinforcement Learning

Han Wang, Erfan Miahi, Martha White, Marlos C. Machado, Zaheer Abbas, Raksha Kumaraswamy, Vincent Liu, Adam White

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

2206.01311 2023-05-01 cs.LG 57%

Learning Soft Constraints From Constrained Expert Demonstrations

Ashish Gaurav, Kasra Rezaee, Guiliang Liu, Pascal Poupart

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

Comments ICLR 2023 camera ready version (incl. supplementary material)

2304.12502 2023-04-26 cs.LG cs.IT eess.SP math.IT stat.ME 57%

Causal Semantic Communication for Digital Twins: A Generalizable Imitation Learning Approach

Christo Kurisummoottil Thomas, Walid Saad, Yong Xiao

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

2304.09996 2023-04-21 cs.RO 57%

Robust Route Planning with Distributional Reinforcement Learning in a Stochastic Road Network Environment

Xi Lin, Paul Szenher, John D. Martin, Brendan Englot

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

Comments The 20th International Conference on Ubiquitous Robots (UR 2023)

2206.02462 2023-04-21 cs.RO 57%

Achieving Goals using Reward Shaping and Curriculum Learning

Mihai Anca, Jonathan D. Thomas, Dabal Pedamonti, Matthew Studley, Mark Hansen

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

Comments To be published at Future Technologies Conference (FTC) 2023

2210.00596 2023-04-20 cs.LG 57%

Policy Gradients for Probabilistic Constrained Reinforcement Learning

Weiqin Chen, Dharmashankar Subramanian, Santiago Paternain

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

2304.05271 2023-04-12 cs.AI 57%

Automaton-Guided Curriculum Generation for Reinforcement Learning Agents

Yash Shukla, Abhishek Kulkarni, Robert Wright, Alvaro Velasquez, Jivko Sinapov

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

Comments To be presented at The International Conference on Automated Planning and Scheduling (ICAPS) 2023

2304.00026 2023-04-04 cs.LG 57%

Understanding Reinforcement Learning Algorithms: The Progress from Basic Q-learning to Proximal Policy Optimization

Mohamed-Amine Chadi, Hajar Mousannif

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

2303.16427 2023-03-30 cs.RO 57%

Learning Excavation of Rigid Objects with Offline Reinforcement Learning

Shiyu Jin, Zhixian Ye, Liangjun Zhang

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

Comments Submitted to IROS 2023

2303.16194 2023-03-29 cs.LG 57%

BC-IRL: Learning Generalizable Reward Functions from Demonstrations

Andrew Szot, Amy Zhang, Dhruv Batra, Zsolt Kira, Franziska Meier

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

2303.11191 2023-03-21 cs.LG 57%

A Survey of Demonstration Learning

André Correia, Luís A. Alexandre

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

Comments 35 pages, 9 figures

2303.08745 2023-03-16 eess.SY cs.RO cs.SY 57%

Real-Time Measurement-Driven Reinforcement Learning Control Approach for Uncertain Nonlinear Systems

Mohammed Abouheaf, Derek Boase, Wail Gueaieb, Davide Spinello, Salah Al-Sharhan

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

Comments 15 pages

Journal ref Engineering Applications of Artificial Intelligence (Elsevier), vol. 122, June 2023

2303.02215 2023-03-07 cs.RO 57%

Learning Stabilization Control from Observations by Learning Lyapunov-like Proxy Models

Milan Ganai, Chiaki Hirayama, Ya-Chien Chang, Sicun Gao

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

Comments ICRA 2023

2109.13338 2023-03-02 cs.RO 57%

Solving Challenging Control Problems Using Two-Staged Deep Reinforcement Learning

Nitish Sontakke, Sehoon Ha

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

Comments The supplemental video can be found at: https://youtu.be/FYLo1Ov_8-g

2302.14242 2023-03-01 cs.RO 57%

Learning Sparse Control Tasks from Pixels by Latent Nearest-Neighbor-Guided Explorations

Ruihan Zhao, Ufuk Topcu, Sandeep Chinchali, Mariano Phielipp

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

2302.13328 2023-02-28 cs.RO 57%

Reinforcement Learning Based Pushing and Grasping Objects from Ungraspable Poses

Hao Zhang, Hongzhuo Liang, Lin Cong, Jianzhi Lyu, Long Zeng, Pingfa Feng, Jianwei Zhang

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

Comments Accepted by ICRA 2023; Project page https://haozhang990127.github.io/PaG/

2209.05738 2023-02-28 cs.RO cs.MA 57%

RTAW: An Attention Inspired Reinforcement Learning Method for Multi-Robot Task Allocation in Warehouse Environments

Aakriti Agrawal, Amrit Singh Bedi, Dinesh Manocha

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

Journal ref ICRA 2023

2302.09522 2023-02-21 cs.CV 57%

Interactive Video Corpus Moment Retrieval using Reinforcement Learning

Zhixin Ma, Chong-Wah Ngo

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

Comments Accepted by ACM Multimedia 2022

Journal ref Proceedings of the 30th ACM International Conference on Multimedia (2022) 296-306

1. 模仿学习与强化学习 4116 篇

A newborn embodied Turing test for view-invariant object recognition

Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning

5G Network on Wings: A Deep Reinforcement Learning Approach to the UAV-based Integrated Access and Backhaul

MARC: A multi-agent robots control framework for enhancing reinforcement learning in construction tasks

EvoTorch: Scalable Evolutionary Computation in Python

Understanding the World to Solve Social Dilemmas Using Multi-Agent Reinforcement Learning

Finite Time Lyapunov Exponent Analysis of Model Predictive Control and Reinforcement Learning

Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges

Multi-Agent Deep Reinforcement Learning For Persistent Monitoring With Sensing, Communication, and Localization Constraints

Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path

Knowledge Transfer from Teachers to Learners in Growing-Batch Reinforcement Learning

Deconstructing deep active inference

Investigating the Properties of Neural Network Representations in Reinforcement Learning

Learning Soft Constraints From Constrained Expert Demonstrations

Causal Semantic Communication for Digital Twins: A Generalizable Imitation Learning Approach

Robust Route Planning with Distributional Reinforcement Learning in a Stochastic Road Network Environment

Achieving Goals using Reward Shaping and Curriculum Learning

Policy Gradients for Probabilistic Constrained Reinforcement Learning

Automaton-Guided Curriculum Generation for Reinforcement Learning Agents

Understanding Reinforcement Learning Algorithms: The Progress from Basic Q-learning to Proximal Policy Optimization

Learning Excavation of Rigid Objects with Offline Reinforcement Learning

BC-IRL: Learning Generalizable Reward Functions from Demonstrations

A Survey of Demonstration Learning

Real-Time Measurement-Driven Reinforcement Learning Control Approach for Uncertain Nonlinear Systems

Learning Stabilization Control from Observations by Learning Lyapunov-like Proxy Models

Solving Challenging Control Problems Using Two-Staged Deep Reinforcement Learning

Learning Sparse Control Tasks from Pixels by Latent Nearest-Neighbor-Guided Explorations

Reinforcement Learning Based Pushing and Grasping Objects from Ungraspable Poses

RTAW: An Attention Inspired Reinforcement Learning Method for Multi-Robot Task Allocation in Warehouse Environments

Interactive Video Corpus Moment Retrieval using Reinforcement Learning