Zobrazeno 1 - 10
of 48
pro vyhledávání: '"Fu, Justin"'
Autor:
Gulino, Cole, Fu, Justin, Luo, Wenjie, Tucker, George, Bronstein, Eli, Lu, Yiren, Harb, Jean, Pan, Xinlei, Wang, Yan, Chen, Xiangyu, Co-Reyes, John D., Agarwal, Rishabh, Roelofs, Rebecca, Lu, Yao, Montali, Nico, Mougin, Paul, Yang, Zoey, White, Brandyn, Faust, Aleksandra, McAllister, Rowan, Anguelov, Dragomir, Sapp, Benjamin
Simulation is an essential tool to develop and benchmark autonomous vehicle planning software in a safe and cost-effective manner. However, realistic simulation requires accurate modeling of nuanced and complex multi-agent interactive behaviors. To a
Externí odkaz:
http://arxiv.org/abs/2310.08710
Autor:
Lu, Yiren, Fu, Justin, Tucker, George, Pan, Xinlei, Bronstein, Eli, Roelofs, Rebecca, Sapp, Benjamin, White, Brandyn, Faust, Aleksandra, Whiteson, Shimon, Anguelov, Dragomir, Levine, Sergey
Imitation learning (IL) is a simple and powerful way to use high-quality human driving data, which can be collected at scale, to produce human-like behavior. However, policies based on imitation learning alone often fail to sufficiently account for s
Externí odkaz:
http://arxiv.org/abs/2212.11419
Autor:
Bronstein, Eli, Palatucci, Mark, Notz, Dominik, White, Brandyn, Kuefler, Alex, Lu, Yiren, Paul, Supratik, Nikdel, Payam, Mougin, Paul, Chen, Hongge, Fu, Justin, Abrams, Austin, Shah, Punit, Racah, Evan, Frenkel, Benjamin, Whiteson, Shimon, Anguelov, Dragomir
Publikováno v:
IEEE/RSJ international conference on intelligent robots and systems (IROS) 2022, pages 8652-8659
We demonstrate the first large-scale application of model-based generative adversarial imitation learning (MGAIL) to the task of dense urban self-driving. We augment standard MGAIL using a hierarchical model to enable generalization to arbitrary goal
Externí odkaz:
http://arxiv.org/abs/2210.09539
Conventionally, generation of natural language for dialogue agents may be viewed as a statistical learning problem: determine the patterns in human-provided data and generate appropriate responses with similar statistical properties. However, dialogu
Externí odkaz:
http://arxiv.org/abs/2204.08426
Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control. While supervised learning with large language models is capable of producing realistic text, how to steer such responses towards completing
Externí odkaz:
http://arxiv.org/abs/2204.10198
Autor:
Fu, Justin, Norouzi, Mohammad, Nachum, Ofir, Tucker, George, Wang, Ziyu, Novikov, Alexander, Yang, Mengjiao, Zhang, Michael R., Chen, Yutian, Kumar, Aviral, Paduraru, Cosmin, Levine, Sergey, Paine, Tom Le
Off-policy evaluation (OPE) holds the promise of being able to leverage large, offline datasets for both evaluating and selecting complex policies for decision making. The ability to learn offline is particularly important in many real-world domains,
Externí odkaz:
http://arxiv.org/abs/2103.16596
Autor:
Fu, Justin, Levine, Sergey
In this work we consider data-driven optimization problems where one must maximize a function given only queries at a fixed set of points. This problem setting emerges in many domains where function evaluation is a complex and expensive process, such
Externí odkaz:
http://arxiv.org/abs/2102.07970
In this tutorial article, we aim to provide the reader with the conceptual tools needed to get started on research on offline reinforcement learning algorithms: reinforcement learning algorithms that utilize previously collected data, without additio
Externí odkaz:
http://arxiv.org/abs/2005.01643
The offline reinforcement learning (RL) setting (also known as full batch RL), where a policy is learned from a static dataset, is compelling as progress enables RL methods to take advantage of large, previously-collected datasets, much like how the
Externí odkaz:
http://arxiv.org/abs/2004.07219
Autor:
Ghosh, Dibya, Gupta, Abhishek, Reddy, Ashwin, Fu, Justin, Devin, Coline, Eysenbach, Benjamin, Levine, Sergey
Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it requires acc
Externí odkaz:
http://arxiv.org/abs/1912.06088