Zobrazeno 1 - 10
of 77
pro vyhledávání: '"Wurman, Peter"'
Autor:
Lee, Hojoon, Hwang, Dongyoon, Kim, Donghu, Kim, Hyunseung, Tai, Jun Jet, Subramanian, Kaushik, Wurman, Peter R., Choo, Jaegul, Stone, Peter, Seno, Takuma
Recent advances in CV and NLP have been largely driven by scaling up the number of network parameters, despite traditional theories suggesting that larger networks are prone to overfitting. These large networks avoid overfitting by integrating compon
Externí odkaz:
http://arxiv.org/abs/2410.09754
Autor:
Vasco, Miguel, Seno, Takuma, Kawamoto, Kenta, Subramanian, Kaushik, Wurman, Peter R., Stone, Peter
Racing autonomous cars faster than the best human drivers has been a longstanding grand challenge for the fields of Artificial Intelligence and robotics. Recently, an end-to-end deep reinforcement learning agent met this challenge in a high-fidelity
Externí odkaz:
http://arxiv.org/abs/2406.12563
Modern reinforcement learning systems produce many high-quality policies throughout the learning process. However, to choose which policy to actually deploy in the real world, they must be tested under an intractable number of environmental condition
Externí odkaz:
http://arxiv.org/abs/2306.07372
Publikováno v:
Transactions on Machine Learning Research, 2023
Experience replay (ER) is a crucial component of many deep reinforcement learning (RL) systems. However, uniform sampling from an ER buffer can lead to slow convergence and unstable asymptotic behaviors. This paper introduces Stratified Sampling from
Externí odkaz:
http://arxiv.org/abs/2211.00576
Autor:
MacGlashan, James, Archer, Evan, Devlic, Alisa, Seno, Takuma, Sherstan, Craig, Wurman, Peter R., Stone, Peter
Designing reinforcement learning (RL) agents is typically a difficult process that requires numerous design iterations. Learning can fail for a multitude of reasons, and standard RL methods provide too few tools to provide insight into the exact caus
Externí odkaz:
http://arxiv.org/abs/2206.13901
Autor:
Kompella, Varun, Capobianco, Roberto, Jong, Stacy, Browne, Jonathan, Fox, Spencer, Meyers, Lauren, Wurman, Peter, Stone, Peter
The year 2020 has seen the COVID-19 virus lead to one of the worst global pandemics in history. As a result, governments around the world are faced with the challenge of protecting public health, while keeping the economy running to the greatest exte
Externí odkaz:
http://arxiv.org/abs/2010.10560
Autor:
Correll, Nikolaus, Bekris, Kostas E., Berenson, Dmitry, Brock, Oliver, Causo, Albert, Hauser, Kris, Okada, Kei, Rodriguez, Alberto, Romano, Joseph M., Wurman, Peter R.
This paper presents a overview of the inaugural Amazon Picking Challenge along with a summary of a survey conducted among the 26 participating teams. The challenge goal was to design an autonomous robot to pick items from a warehouse shelf. This task
Externí odkaz:
http://arxiv.org/abs/1601.05484
Autor:
Wurman, Peter R., Wellman, Michael P.
We examine a standard factory scheduling problem with stochastic processing and setup times, minimizing the expectation of the weighted number of tardy jobs. Because the costs of operators in the schedule are stochastic and sequence dependent, standa
Externí odkaz:
http://arxiv.org/abs/1302.3611
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Wurman, Peter R.1 peter.wurman@sony.com, Stone, Peter1,2 pstone@cs.utexas.edu, Spranger, Michael3 michael.spranger@sony.com
Publikováno v:
Science. 7/14/2023, Vol. 381 Issue 6654, p147-148. 2p. 1 Color Photograph.
