Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Xie, Amber"'
Few-shot imitation learning relies on only a small amount of task-specific demonstrations to efficiently adapt a policy for a given downstream tasks. Retrieval-based methods come with a promise of retrieving relevant past experiences to augment this
Externí odkaz:
http://arxiv.org/abs/2408.16944
Layout design, such as user interface or graphical layout in general, is fundamentally an iterative revision process. Through revising a design repeatedly, the designer converges on an ideal layout. In this paper, we investigate how revision edits fr
Externí odkaz:
http://arxiv.org/abs/2406.18559
Learning from human feedback has shown success in aligning large, pretrained models with human values. Prior works have mostly focused on learning from high-level labels, such as preferences between pairs of model outputs. On the other hand, many dom
Externí odkaz:
http://arxiv.org/abs/2405.13026
Contact is at the core of robotic manipulation. At times, it is desired (e.g. manipulation and grasping), and at times, it is harmful (e.g. when avoiding obstacles). However, traditional path planning algorithms focus solely on collision-free paths,
Externí odkaz:
http://arxiv.org/abs/2308.16893
Autor:
Adeniji, Ademi, Xie, Amber, Sferrazza, Carmelo, Seo, Younggyo, James, Stephen, Abbeel, Pieter
Using learned reward functions (LRFs) as a means to solve sparse-reward reinforcement learning (RL) tasks has yielded some steady progress in task-complexity through the years. In this work, we question whether today's LRFs are best-suited as a direc
Externí odkaz:
http://arxiv.org/abs/2308.12270
Diffusion models have shown impressive results in text-to-image synthesis. Using massive datasets of captioned images, diffusion models learn to generate raster images of highly diverse objects and scenes. However, designers frequently use vector rep
Externí odkaz:
http://arxiv.org/abs/2211.11319
Autor:
So, John, Xie, Amber, Jung, Sunggoo, Edlund, Jeffrey, Thakker, Rohan, Agha-mohammadi, Ali, Abbeel, Pieter, James, Stephen
Autonomous driving is complex, requiring sophisticated 3D scene understanding, localization, mapping, and control. Rather than explicitly modelling and fusing each of these components, we instead consider an end-to-end approach via reinforcement lear
Externí odkaz:
http://arxiv.org/abs/2210.14721
While unsupervised skill discovery has shown promise in autonomously acquiring behavioral primitives, there is still a large methodological disconnect between task-agnostic skill pretraining and downstream, task-aware finetuning. We present Intrinsic
Externí odkaz:
http://arxiv.org/abs/2210.07426