机器人 / 具身智能 - arXivDaily 专题

2009.02653 2023-02-28 cs.LG cs.CV stat.ML 62%

A Survey on Machine Learning from Few Samples

Jiang Lu, Pinghua Gong, Jieping Ye, Jianwei Zhang, Changshui Zhang

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

Comments 30 pages, Accepted by Pattern Recognition, 2023

Journal ref Pattern Recognition, 2023

2302.12349 2023-02-27 cs.LG cs.AI stat.ML 62%

Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws

Kush Bhatia, Wenshuo Guo, Jacob Steinhardt

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

Comments Accepted to AISTATS 2023

2203.11197 2023-02-21 cs.LG cs.AI 62%

Teachable Reinforcement Learning via Advice Distillation

Olivia Watkins, Trevor Darrell, Pieter Abbeel, Jacob Andreas, Abhishek Gupta

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 2021

2302.08865 2023-02-20 cs.LG cs.AI 62%

Swapped goal-conditioned offline reinforcement learning

Wenyan Yang, Huiling Wang, Dingding Cai, Joni Pajarinen, Joni-Kristen Kämäräinen

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

Comments arXiv admin note: text overlap with arXiv:2302.07741

2109.06668 2023-02-03 cs.AI cs.LG cs.MA 62%

Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain

Jianye Hao, Tianpei Yang, Hongyao Tang, Chenjia Bai, Jinyi Liu, Zhaopeng Meng, Peng Liu, Zhen Wang

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

Comments Accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

2211.11096 2023-01-31 cs.LG cs.AI cs.NE 62%

Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows

Dmitriy Akimov, Vladislav Kurenkov, Alexander Nikulin, Denis Tarasov, Sergey Kolesnikov

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

Comments Accepted at 3rd Offline Reinforcement Learning Workshop at Neural Information Processing Systems, 2022. Source code: https://github.com/tinkoff-ai/cnf

2301.10067 2023-01-25 cs.LG cs.AI 62%

Intrinsic Motivation in Model-based Reinforcement Learning: A Brief Review

Artem Latyshev, Aleksandr I. Panov

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

Comments 13 pages, 7 figures

2301.09544 2023-01-24 cs.RO cs.CV 62%

Learning to View: Decision Transformers for Active Object Detection

Wenhao Ding, Nathalie Majcherczyk, Mohit Deshpande, Xuewei Qi, Ding Zhao, Rajasimman Madhivanan, Arnie Sen

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

Comments Accepted to ICRA 2023

2301.05392 2023-01-16 cs.CV cs.LG 62%

Multi-Target Landmark Detection with Incomplete Images via Reinforcement Learning and Shape Prior

Kaiwen Wan, Lei Li, Dengqiang Jia, Shangqi Gao, Wei Qian, Yingzhi Wu, Huandong Lin, Xiongzheng Mu, Xin Gao, Sijia Wang, Fuping Wu, Xiahai Zhuang

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

Comments 29 pages, 13 figures

2301.00650 2023-01-03 cs.RO cs.AI 62%

Hybrid Deep Reinforcement Learning and Planning for Safe and Comfortable Automated Driving

Dikshant Gupta, Mathias Klusch

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

2301.00188 2023-01-03 cs.LG cs.AI cs.CR 62%

New Challenges in Reinforcement Learning: A Survey of Security and Privacy

Yunjiao Lei, Dayong Ye, Sheng Shen, Yulei Sui, Tianqing Zhu, Wanlei Zhou

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

2212.13936 2022-12-29 cs.LG cs.AI stat.ME stat.ML 62%

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

Tim G. J. Rudner, Cong Lu, Michael A. Osborne, Yarin Gal, Yee Whye Teh

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

Comments Published in Advances in Neural Information Processing Systems 34 (NeurIPS 2021)

2104.10190 2022-12-29 cs.LG cs.AI stat.ME stat.ML 62%

Outcome-Driven Reinforcement Learning via Variational Inference

Tim G. J. Rudner, Vitchyr H. Pong, Rowan McAllister, Yarin Gal, Sergey Levine

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

Comments Published in Advances in Neural Information Processing Systems 34 (NeurIPS 2021)

2212.12786 2022-12-27 cs.RO cs.LG 62%

SHIRO: Soft Hierarchical Reinforcement Learning

Kandai Watanabe, Mathew Strong, Omer Eldar

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

2212.10064 2022-12-21 cs.RO cs.LG cs.MA cs.SY eess.SY math.OC 62%

AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learning

Aowabin Rahman, Arnab Bhattacharya, Thiagarajan Ramachandran, Sayak Mukherjee, Himanshu Sharma, Ted Fujimoto, Samrat Chatterjee

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

2212.08961 2022-12-20 cs.LG cs.RO 62%

Training Robots to Evaluate Robots: Example-Based Interactive Reward Functions for Policy Learning

Kun Huang, Edward S. Hu, Dinesh Jayaraman

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

Comments CoRL 2022

2212.08232 2022-12-19 cs.LG cs.RO 62%

Offline Robot Reinforcement Learning with Uncertainty-Guided Human Expert Sampling

Ashish Kumar, Ilya Kuzovkin

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

2212.06988 2022-12-15 cs.LG cs.AI 62%

Efficient Exploration in Resource-Restricted Reinforcement Learning

Zhihai Wang, Taoxing Pan, Qi Zhou, Jie Wang

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

Comments Accepted to AAAI 2023

2212.05727 2022-12-13 cs.LG cs.RO 62%

Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks

Linrui Zhang, Qin Zhang, Li Shen, Bo Yuan, Xueqian Wang, Dacheng Tao

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

Comments 37th AAAI Conference on Artificial Intelligence (AAAI-23)

2212.04603 2022-12-12 cs.LG cs.AI 62%

System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Games

Indranil Sur, Zachary Daniels, Abrar Rahman, Kamil Faber, Gianmarco J. Gallardo, Tyler L. Hayes, Cameron E. Taylor, Mustafa Burak Gurbuz, James Smith, Sahana Joshi, Nathalie Japkowicz, Michael Baron, Zsolt Kira, Christopher Kanan, Roberto Corizzo, Ajay Divakaran, Michael Piacentino, Jesse Hostetler, Aswin Raghavan

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

Comments The Second International Conference on AIML Systems, October 12--15, 2022, Bangalore, India

2212.02909 2022-12-07 cs.AI cs.MA cs.RO 62%

Scalable Planning and Learning Framework Development for Swarm-to-Swarm Engagement Problems

Umut Demir, A. Sadik Satir, Gulay Goktas Sever, Cansu Yikilmaz, Nazim Kemal Ure

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

Comments Accepted to SciTech2023

2102.00824 2022-12-05 cs.MA cs.AI cs.LG 62%

HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging

Nikunj Gupta, G Srinivasaraghavan, Swarup Kumar Mohalik, Nishant Kumar, Matthew E. Taylor

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

2211.14663 2022-11-29 cs.AI cs.NE cs.RO 62%

Computational Co-Design for Variable Geometry Truss

Jianzhe Gu, Lining Yao

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

2210.05150 2022-11-22 cs.LG cs.AI 62%

DHRL: A Graph-Based Approach for Long-Horizon and Sparse Hierarchical Reinforcement Learning

Seungjae Lee, Jigang Kim, Inkyu Jang, H. Jin Kim

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

Comments Accepted to NeurIPS 2022 (Selected as Oral)

2211.10168 2022-11-21 cs.LG cs.RO 62%

Language-Conditioned Reinforcement Learning to Solve Misunderstandings with Action Corrections

Frank Röder, Manfred Eppe

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

Comments Accepted to the 2nd Workshop on Language in Reinforcement Learning, (NeurIPS 2022)

2211.09382 2022-11-18 cs.RO cs.CV 62%

Planning Irregular Object Packing via Hierarchical Reinforcement Learning

Sichao Huang, Ziwei Wang, Jie Zhou, Jiwen Lu

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

Comments This work is accepted by IEEE RAL. 8 pages, 6 figures

2211.06929 2022-11-15 cs.LG cs.AI 62%

Goal-Conditioned Reinforcement Learning in the Presence of an Adversary

Carlos Purves, Pietro Liò, Cătălina Cangea

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

2012.13490 2022-11-15 cs.LG cs.AI 62%

Towards Continual Reinforcement Learning: A Review and Perspectives

Khimya Khetarpal, Matthew Riemer, Irina Rish, Doina Precup

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

Comments Journal of Artificial Intelligence Research (JAIR)

2209.08842 2022-11-11 cs.LG cs.AI 62%

Rewarding Episodic Visitation Discrepancy for Exploration in Reinforcement Learning

Mingqi Yuan, Bo Li, Xin Jin, Wenjun Zeng

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

Comments 16 pages, 9 figures; Deep RL Workshop NeurIPS 2022

2211.03959 2022-11-09 cs.LG cs.AI 62%

Pretraining in Deep Reinforcement Learning: A Survey

Zhihui Xie, Zichuan Lin, Junyou Li, Shuai Li, Deheng Ye

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 4134 篇

A Survey on Machine Learning from Few Samples

Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws

Teachable Reinforcement Learning via Advice Distillation

Swapped goal-conditioned offline reinforcement learning

Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain

Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows

Intrinsic Motivation in Model-based Reinforcement Learning: A Brief Review

Learning to View: Decision Transformers for Active Object Detection

Multi-Target Landmark Detection with Incomplete Images via Reinforcement Learning and Shape Prior

Hybrid Deep Reinforcement Learning and Planning for Safe and Comfortable Automated Driving

New Challenges in Reinforcement Learning: A Survey of Security and Privacy

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

Outcome-Driven Reinforcement Learning via Variational Inference

SHIRO: Soft Hierarchical Reinforcement Learning

AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learning

Training Robots to Evaluate Robots: Example-Based Interactive Reward Functions for Policy Learning

Offline Robot Reinforcement Learning with Uncertainty-Guided Human Expert Sampling

Efficient Exploration in Resource-Restricted Reinforcement Learning

Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks

System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Games

Scalable Planning and Learning Framework Development for Swarm-to-Swarm Engagement Problems

HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging

Computational Co-Design for Variable Geometry Truss

DHRL: A Graph-Based Approach for Long-Horizon and Sparse Hierarchical Reinforcement Learning

Language-Conditioned Reinforcement Learning to Solve Misunderstandings with Action Corrections

Planning Irregular Object Packing via Hierarchical Reinforcement Learning

Goal-Conditioned Reinforcement Learning in the Presence of an Adversary

Towards Continual Reinforcement Learning: A Review and Perspectives

Rewarding Episodic Visitation Discrepancy for Exploration in Reinforcement Learning

Pretraining in Deep Reinforcement Learning: A Survey