Learning modular language-conditioned robot policies through attention

[Free GPT-4]
[PDF] arxiv.org

Explaining agent behavior with large language models

X Zhang, Y Guo, S Stepputtis, K Sycara… - ar** versatile, general-purpose agents. These limitations …
Speichern Zitieren Zitiert von: 3 Ähnliche Artikel Alle 3 Versionen HTML-Version
[Free GPT-4]
[PDF] arxiv.org

Negative Yields Positive: Unified Dual-Path Adapter for Vision-Language Models

C Zhang, S Stepputtis, K Sycara, Y ** with Large Language Models through Geometric Decomposition
S Li, S Bhagat, J Campbell, Y ** of unfamiliar objects is a necessary skill for robots in dynamic in-
home environments. Inspired by the human capability to grasp such objects through intuition …
Speichern Zitieren Zitiert von: 6 Ähnliche Artikel Alle 2 Versionen HTML-Version
[Free GPT-4]
[PDF] cmu.edu

[PDF][PDF] Enhancing Policy Transfer in Action Advising for Reinforcement Learning

Y Guo - 2024 - reports-archive.adm.cs.cmu.edu
As human students benefit from teachers' advice to accelerate their learning, so could
agents benefit from advice. Agents can not only learn from humans, eg via human expert …
Speichern Zitieren Ähnliche Artikel Alle 2 Versionen HTML-Version
[Free GPT-4]
[PDF] github.io

[PDF][PDF] AutoMA: Automated Modular Attention enables Context-Rich Imitation Learning using Foundation Models

Y Zhou, X Liu, Q Vuong, HB Amor - auto-ma.github.io
Although imitation learning offers an appealing framework for policy learning, scaling it is
challenging due to the lack of high-quality expert data. Previous works have addressed this …
Speichern Zitieren Ähnliche Artikel HTML-Version