How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulation-Reference-Cited by-同舟云学术

How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulation

Published:2022-10-23 Issue: Volume: Page:
ISSN:
Container-title:2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
language:
Short-container-title:

Author:

Lee Alex X.¹,Devin Coline¹,Springenberg Jost Tobias¹,Zhou Yuxiang¹,Lampe Thomas¹,Abdolmaleki Abbas¹,Bousmalis Konstantinos¹

Affiliation:

1. DeepMind,London,UK

Publisher

IEEE

Link

Reference26 articles.

1. A minimalist approach to offline reinforcement learning;fujimoto;NeurIPS,2021

2. Keep doing what worked: Behavior modelling priors for offline reinforcement learning;siegel;ICLRE,2019

Cited by 5 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Efficient Offline Reinforcement Learning With Relaxed Conservatism;IEEE Transactions on Pattern Analysis and Machine Intelligence;2024-08

2. Conditionally Combining Robot Skills using Large Language Models;2024 IEEE International Conference on Robotics and Automation (ICRA);2024-05-13

4. GPTMORE: Generative Pre-trained Transformer for Model-based Offline Reinforcement Learning;2023 Asia Conference on Cognitive Engineering and Intelligent Interaction (CEII);2023-12-15

5. Learning from Pixels with Expert Observations;2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS);2023-10-01