机器人 / 具身智能 - arXivDaily 专题

2312.14134 2024-08-12 cs.LG cs.CV cs.RO 75%

Diffusion Reward: Learning Rewards via Conditional Video Diffusion

Tao Huang, Guangqi Jiang, Yanjie Ze, Huazhe Xu

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

Comments Accepted to ECCV 2024. Project page and code: https://diffusion-reward.github.io/

2407.16186 2024-07-24 cs.RO cs.AI cs.LG 75%

Automatic Environment Shaping is the Next Frontier in RL

Younghyo Park, Gabriel B. Margolis, Pulkit Agrawal

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

Comments ICML 2024 Position Track; Website at https://auto-env-shaping.github.io/

2402.15567 2024-05-28 cs.LG cs.AI cs.RO 75%

Foundation Policies with Hilbert Representations

Seohong Park, Tobias Kreiman, Sergey Levine

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

Comments ICML 2024

2309.11489 2024-05-28 cs.LG cs.AI cs.CL cs.RO 75%

Text2Reward: Reward Shaping with Language Models for Reinforcement Learning

Tianbao Xie, Siheng Zhao, Chen Henry Wu, Yitao Liu, Qian Luo, Victor Zhong, Yanchao Yang, Tao Yu

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

Comments ICLR 2024 camera ready, 37 pages, 12 figures

2405.14853 2024-05-24 cs.LG cs.AI cs.RO 75%

Privileged Sensing Scaffolds Reinforcement Learning

Edward S. Hu, James Springer, Oleh Rybkin, Dinesh Jayaraman

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

Comments ICLR 2024 Spotlight version

2405.04714 2024-05-09 cs.RO cs.AI cs.LG 75%

RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes

Kyle Stachowicz, Sergey Levine

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

Comments In review, RSS 2024

2405.04307 2024-05-08 cs.RO cs.AI cs.LG 75%

Improving Offline Reinforcement Learning with Inaccurate Simulators

Yiwen Hou, Haoyuan Sun, Jinming Ma, Feng Wu

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

2402.03678 2024-04-04 cs.AI cs.LG cs.RO 75%

Logical Specifications-guided Dynamic Task Sampling for Reinforcement Learning Agents

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

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

2310.06171 2024-03-19 cs.LG cs.AI cs.RO 75%

Memory-Consistent Neural Networks for Imitation Learning

Kaustubh Sridhar, Souradeep Dutta, Dinesh Jayaraman, James Weimer, Insup Lee

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

Comments ICLR 2024. 26 pages (9 main pages)

2310.05905 2024-03-11 cs.LG cs.AI cs.RO 75%

TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models

Zuxin Liu, Jesse Zhang, Kavosh Asadi, Yao Liu, Ding Zhao, Shoham Sabach, Rasool Fakoor

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

Comments Published on ICLR 2024

2402.15757 2024-02-27 cs.LG cs.AI cs.RO stat.ML 75%

Batch Active Learning of Reward Functions from Human Preferences

Erdem Bıyık, Nima Anari, Dorsa Sadigh

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

Comments To appear in ACM Transactions on Human-Robot Interaction (THRI). 27 pages, 12 figures, 2 tables. arXiv admin note: text overlap with arXiv:1810.04303

2402.13201 2024-02-21 cs.RO cs.AI cs.LG 75%

Tiny Reinforcement Learning for Quadruped Locomotion using Decision Transformers

Orhan Eren Akgün, Néstor Cuevas, Matheus Farias, Daniel Garces

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

Comments 10 pages, 4 figures

2306.00975 2023-11-07 cs.LG cs.CV cs.RO 75%

Active Vision Reinforcement Learning under Limited Visual Observability

Jinghuan Shang, Michael S. Ryoo

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

Comments NeurIPS 2023. Project page at https://elicassion.github.io/sugarl/sugarl.html Code at https://github.com/elicassion/sugarl Environment library at https://github.com/elicassion/active-gym

2310.15145 2023-10-24 cs.RO cs.AI cs.LG 75%

Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning

Jingyun Yang, Max Sobol Mark, Brandon Vu, Archit Sharma, Jeannette Bohg, Chelsea Finn

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

2309.10150 2023-10-18 cs.RO cs.AI cs.LG 75%

Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions

Yevgen Chebotar, Quan Vuong, Alex Irpan, Karol Hausman, Fei Xia, Yao Lu, Aviral Kumar, Tianhe Yu, Alexander Herzog, Karl Pertsch, Keerthana Gopalakrishnan, Julian Ibarz, Ofir Nachum, Sumedh Sontakke, Grecia Salazar, Huong T Tran, Jodilyn Peralta, Clayton Tan, Deeksha Manjunath, Jaspiar Singht, Brianna Zitkovich, Tomas Jackson, Kanishka Rao, Chelsea Finn, Sergey Levine

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

Comments See website at https://qtransformer.github.io

2310.08836 2023-10-16 cs.RO cs.AI cs.LG 75%

A Framework for Few-Shot Policy Transfer through Observation Mapping and Behavior Cloning

Yash Shukla, Bharat Kesari, Shivam Goel, Robert Wright, Jivko Sinapov

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

Comments Paper accepted to the IROS 2023 Conference

2309.10175 2023-09-20 cs.RO cs.AI cs.LG 75%

One ACT Play: Single Demonstration Behavior Cloning with Action Chunking Transformers

Abraham George, Amir Barati Farimani

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

Comments 7 pages, 6 figures

2307.11954 2023-07-25 cs.RO cs.AI cs.LG 75%

On-Robot Bayesian Reinforcement Learning for POMDPs

Hai Nguyen, Sammie Katt, Yuchen Xiao, Christopher Amato

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

Comments Accepted at IROS-2023 (Detroit, USA)

2307.09668 2023-07-20 cs.RO cs.AI cs.LG 75%

Towards A Unified Agent with Foundation Models

Norman Di Palo, Arunkumar Byravan, Leonard Hasenclever, Markus Wulfmeier, Nicolas Heess, Martin Riedmiller

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

2306.07552 2023-06-14 cs.LG cs.AI cs.RO 75%

Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second

Vincent-Pierre Berges, Andrew Szot, Devendra Singh Chaplot, Aaron Gokaslan, Roozbeh Mottaghi, Dhruv Batra, Eric Undersander

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

2306.06799 2023-06-13 cs.RO cs.AI cs.LG 75%

On the Efficacy of 3D Point Cloud Reinforcement Learning

Zhan Ling, Yunchao Yao, Xuanlin Li, Hao Su

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

2211.05551 2023-06-06 cs.LG cs.AI cs.RO 75%

Causal Counterfactuals for Improving the Robustness of Reinforcement Learning

Tom He, Jasmina Gajcin, Ivana Dusparic

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

Comments Accepted to ARMS-2023 (ARMS-2023: AAMAS 2023 Workshop on Autonomous Robots and Multirobot Systems)

2305.05760 2023-06-02 cs.LG cs.AI cs.RO 75%

Reducing the Cost of Cycle-Time Tuning for Real-World Policy Optimization

Homayoon Farrahi, A. Rupam Mahmood

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

Comments To appear in Proceedings of the 2023 International Joint Conference on Neural Networks (IJCNN). Source code is available at http://github.com/homayoonfarrahi/cycle-time-study and companion video at http://www.youtube.com/watch?v=tmo5fWGRPtk

2304.08742 2023-05-16 cs.RO cs.AI cs.LG 75%

Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets

Maximilian Du, Suraj Nair, Dorsa Sadigh, Chelsea Finn

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

2305.01400 2023-05-03 cs.RO cs.AI cs.LG cs.SY eess.SY 75%

Get Back Here: Robust Imitation by Return-to-Distribution Planning

Geoffrey Cideron, Baruch Tabanpour, Sebastian Curi, Sertan Girgin, Leonard Hussenot, Gabriel Dulac-Arnold, Matthieu Geist, Olivier Pietquin, Robert Dadashi

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

2303.14870 2023-03-28 cs.RO cs.AI cs.LG 75%

Bi-Manual Block Assembly via Sim-to-Real Reinforcement Learning

Satoshi Kataoka, Youngseog Chung, Seyed Kamyar Seyed Ghasemipour, Pannag Sanketi, Shixiang Shane Gu, Igor Mordatch

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

Comments Our accompanying project webpage can be found at: https://sites.google.com/view/u-shape-block-assembly. arXiv admin note: substantial text overlap with arXiv:2203.08277

2210.14685 2023-03-15 cs.LG cs.AI cs.RO 75%

Leveraging Demonstrations with Latent Space Priors

Jonas Gehring, Deepak Gopinath, Jungdam Won, Andreas Krause, Gabriel Synnaeve, Nicolas Usunier

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

Comments Published in Transactions on Machine Learning Research (03/2023)

2303.01488 2023-03-03 cs.RO cs.AI cs.LG 75%

Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning

Archit Sharma, Ahmed M. Ahmed, Rehaan Ahmad, Chelsea Finn

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

2212.05711 2023-02-17 cs.RO cs.AI cs.LG 75%

CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learning

Zhao Mandi, Homanga Bharadhwaj, Vincent Moens, Shuran Song, Aravind Rajeswaran, Vikash Kumar

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

2210.11287 2022-10-21 cs.LG cs.AI cs.RO 75%

MoCoDA: Model-based Counterfactual Data Augmentation

Silviu Pitis, Elliot Creager, Ajay Mandlekar, Animesh Garg

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

Comments In Proceedings of NeurIPS 2022. 10 pages (+3 references, +10 appendix). Code available at https://github.com/spitis/mocoda

1. 模仿学习与强化学习 4111 篇

Diffusion Reward: Learning Rewards via Conditional Video Diffusion

Automatic Environment Shaping is the Next Frontier in RL

Foundation Policies with Hilbert Representations

Text2Reward: Reward Shaping with Language Models for Reinforcement Learning

Privileged Sensing Scaffolds Reinforcement Learning

RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes

Improving Offline Reinforcement Learning with Inaccurate Simulators

Logical Specifications-guided Dynamic Task Sampling for Reinforcement Learning Agents

Memory-Consistent Neural Networks for Imitation Learning

TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models

Batch Active Learning of Reward Functions from Human Preferences

Tiny Reinforcement Learning for Quadruped Locomotion using Decision Transformers

Active Vision Reinforcement Learning under Limited Visual Observability

Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning

Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions

A Framework for Few-Shot Policy Transfer through Observation Mapping and Behavior Cloning

One ACT Play: Single Demonstration Behavior Cloning with Action Chunking Transformers

On-Robot Bayesian Reinforcement Learning for POMDPs

Towards A Unified Agent with Foundation Models

Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second

On the Efficacy of 3D Point Cloud Reinforcement Learning

Causal Counterfactuals for Improving the Robustness of Reinforcement Learning

Reducing the Cost of Cycle-Time Tuning for Real-World Policy Optimization

Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets

Get Back Here: Robust Imitation by Return-to-Distribution Planning

Bi-Manual Block Assembly via Sim-to-Real Reinforcement Learning

Leveraging Demonstrations with Latent Space Priors

Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning

CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learning

MoCoDA: Model-based Counterfactual Data Augmentation