Zobrazeno 1 - 10
of 5 412
pro vyhledávání: '"MURPHY, KEVIN A."'
Autor:
Murphy, Kevin
This manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement learning and sequential decision making, covering value-based RL, policy-gradient methods, model-based methods, and various other topics (including a very b
Externí odkaz:
http://arxiv.org/abs/2412.05265
We propose a mechanism for diffusion generalization based on local denoising operations. Through analysis of network and empirical denoisers, we identify local inductive biases in diffusion models. We demonstrate that local denoising operations can b
Externí odkaz:
http://arxiv.org/abs/2411.19339
Autor:
Duran-Martin, Gerardo, Sánchez-Betancourt, Leandro, Shestopaloff, Alexander Y., Murphy, Kevin
We propose a unifying framework for methods that perform Bayesian online learning in non-stationary environments. We call the framework BONE, which stands for (B)ayesian (O)nline learning in (N)on-stationary (E)nvironments. BONE provides a common str
Externí odkaz:
http://arxiv.org/abs/2411.10153
Autor:
Gururaja, Sireesh, Zhang, Yueheng, Tang, Guannan, Zhang, Tianhao, Murphy, Kevin, Yi, Yu-Tsen, Seo, Junwon, Rollett, Anthony, Strubell, Emma
Recent years in NLP have seen the continued development of domain-specific information extraction tools for scientific documents, alongside the release of increasingly multimodal pretrained transformer models. While the opportunity for scientists out
Externí odkaz:
http://arxiv.org/abs/2410.23478
Autor:
Zhou, Guangyao, Swaminathan, Sivaramakrishnan, Raju, Rajkumar Vasudeva, Guntupalli, J. Swaroop, Lehrach, Wolfgang, Ortiz, Joseph, Dedieu, Antoine, Lázaro-Gredilla, Miguel, Murphy, Kevin
We propose Diffusion Model Predictive Control (D-MPC), a novel MPC approach that learns a multi-step action proposal and a multi-step dynamics model, both using diffusion models, and combines them for use in online MPC. On the popular D4RL benchmark,
Externí odkaz:
http://arxiv.org/abs/2410.05364
Autor:
Ortiz, Joseph, Dedieu, Antoine, Lehrach, Wolfgang, Guntupalli, Swaroop, Wendelken, Carter, Humayun, Ahmad, Zhou, Guangyao, Swaminathan, Sivaramakrishnan, Lázaro-Gredilla, Miguel, Murphy, Kevin
Learning from previously collected data via behavioral cloning or offline reinforcement learning (RL) is a powerful recipe for scaling generalist agents by avoiding the need for expensive online learning. Despite strong generalization in some respect
Externí odkaz:
http://arxiv.org/abs/2409.18330
Autor:
Yan, Su, Vié, Clotilde, Lerendegui, Marcelo, Verinaz-Jadan, Herman, Yan, Jipeng, Tashkova, Martina, Burn, James, Wang, Bingxue, Frost, Gary, Murphy, Kevin G., Tang, Meng-Xing
Super-resolution ultrasound imaging through microbubble (MB) localisation and tracking, also known as ultrasound localisation microscopy, allows non-invasive sub-diffraction resolution imaging of microvasculature in animals and humans. The number of
Externí odkaz:
http://arxiv.org/abs/2407.06373
We propose an approach to simulating trajectories of multiple interacting agents (road users) based on transformers and probabilistic graphical models (PGMs), and apply it to the Waymo SimAgents challenge. The transformer baseline is based on the MTR
Externí odkaz:
http://arxiv.org/abs/2406.19635
Publikováno v:
Advances in Neural Information Processing Systems, 2024
Multiple types of inference are available for probabilistic graphical models, e.g., marginal, maximum-a-posteriori, and even marginal maximum-a-posteriori. Which one do researchers mean when they talk about ``planning as inference''? There is no cons
Externí odkaz:
http://arxiv.org/abs/2406.17863
Publikováno v:
NeurIPS 2024
We propose a novel approach to sequential Bayesian inference based on variational Bayes (VB). The key insight is that, in the online setting, we do not need to add the KL term to regularize to the prior (which comes from the posterior at the previous
Externí odkaz:
http://arxiv.org/abs/2405.19681