Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Karten, Seth"'
Recent advances in reinforcement learning (RL) heavily rely on a variety of well-designed benchmarks, which provide environmental platforms and consistent criteria to evaluate existing and novel algorithms. Specifically, in multi-agent RL (MARL), a p
Externí odkaz:
http://arxiv.org/abs/2406.02081
Explicit communication among humans is key to coordinating and learning. Social learning, which uses cues from experts, can greatly benefit from the usage of explicit communication to align heterogeneous policies, reduce sample complexity, and solve
Externí odkaz:
http://arxiv.org/abs/2302.14276
Communication enables agents to cooperate to achieve their goals. Learning when to communicate, i.e., sparse (in time) communication, and whom to message is particularly important when bandwidth is limited. Recent work in learning sparse individualiz
Externí odkaz:
http://arxiv.org/abs/2212.00115
Neural nets are powerful function approximators, but the behavior of a given neural net, once trained, cannot be easily modified. We wish, however, for people to be able to influence neural agents' actions despite the agents never training with human
Externí odkaz:
http://arxiv.org/abs/2201.12938
Learning interpretable communication is essential for multi-agent and human-agent teams (HATs). In multi-agent reinforcement learning for partially-observable environments, agents may convey information to others via learned communication, allowing t
Externí odkaz:
http://arxiv.org/abs/2201.07452
Publikováno v:
Machine Learning for Motion Planning (MLMP) Workshop at ICRA 2021, Xi'an, China
This paper aims to improve the path quality and computational efficiency of kinodynamic planners used for vehicular systems. It proposes a learning framework for identifying promising controls during the expansion process of sampling-based motion pla
Externí odkaz:
http://arxiv.org/abs/2201.02254
This paper aims to improve the path quality and computational efficiency of sampling-based kinodynamic planners for vehicular navigation. It proposes a learning framework for identifying promising controls during the expansion process of sampling-bas
Externí odkaz:
http://arxiv.org/abs/2110.04238
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Brown, Austin L., Sperling, Daniel, Austin, Bernadette, DeShazo, JR, Fulton, Lew, Lipman, Timothy, Murphy, Colin, Saphores, Jean Daniel, Tal, Gil, Abrams, Carolyn, Chakraborty, Debapriya, Coffee, Daniel, Dabag, Sina, Davis, Adam, Delucchi, Mark A, Fleming, Kelly L, Forest, Kate, Garcia Sanchez, Juan Carlos, Handy, Susan, Hyland, Michael, Jenn, Alan, Karten, Seth, Lane, Blake, Mackinnon, Michael, Martin, Elliot, Miller, Marshall, Ramirez-Ibarra, Monica, Ritchie, Stephen, Schremmer, Sara, Segui, Joshua, Shaheen, Susan, Tok, Andre, Voleti, Aditya, Witcover, Julie, Yang, Allison
The purpose of this report is to provide a research-driven analysis of options that can put California on a pathway to achieve carbon-neutral transportation by 2045. The report comprises thirteen sections. Section 1 provides an overview of the major
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______325::66e52208bf08eef815fec4dd3249d8b1
https://escholarship.org/uc/item/3np3p2t0
https://escholarship.org/uc/item/3np3p2t0
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.