Zobrazeno 1 - 10
of 56 422
pro vyhledávání: '"P. A. Stone"'
Autor:
Wang, Zizhao, Hu, Jiaheng, Chuck, Caleb, Chen, Stephen, Martín-Martín, Roberto, Zhang, Amy, Niekum, Scott, Stone, Peter
Unsupervised skill discovery carries the promise that an intelligent agent can learn reusable skills through autonomous, reward-free environment interaction. Existing unsupervised skill discovery methods learn skills by encouraging distinguishable be
Externí odkaz:
http://arxiv.org/abs/2410.18416
Many robot manipulation tasks require active or interactive exploration behavior in order to be performed successfully. Such tasks are ubiquitous in embodied domains, where agents must actively search for the information necessary for each stage of a
Externí odkaz:
http://arxiv.org/abs/2410.18964
We report a surface instability observed during the extrusion of extremely soft elastic solids in confined geometries. Due to their unique rheological properties, these soft solids can migrate through narrow gaps by continuously everting the bulk mat
Externí odkaz:
http://arxiv.org/abs/2410.14793
Massive black hole (MBH) binaries in galactic nuclei are one of the leading sources of $\sim$ mHz gravitational waves (GWs) for future missions such as $\rm{\textit{LISA}}$. However, the poor sky localization of GW interferometers will make it challe
Externí odkaz:
http://arxiv.org/abs/2410.12911
A hallmark of intelligent agents is the ability to learn reusable skills purely from unsupervised interaction with the environment. However, existing unsupervised skill discovery methods often learn entangled skills where one skill variable simultane
Externí odkaz:
http://arxiv.org/abs/2410.11251
Fragmentation in a gravitationally unstable accretion disk can be an important pathway for forming stellar/planetary companions. To characterize quantitatively the condition for and outcome of fragmentation under realistic thermodynamics, we perform
Externí odkaz:
http://arxiv.org/abs/2410.12042
Light passing near a black hole can follow multiple paths from an emission source to an observer due to strong gravitational lensing. Photons following different paths take different amounts of time to reach the observer, which produces an echo signa
Externí odkaz:
http://arxiv.org/abs/2410.10950
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
In robot planning, tasks can often be achieved through multiple options, each consisting of several actions. This work specifically addresses deadline constraints in task and motion planning, aiming to find a plan that can be executed within the dead
Externí odkaz:
http://arxiv.org/abs/2410.05828
In order to train agents that can quickly adapt to new objectives or reward functions, efficient unsupervised representation learning in sequential decision-making environments can be important. Frameworks such as the Exogenous Block Markov Decision
Externí odkaz:
http://arxiv.org/abs/2410.03016