Search alternatives:
increase decrease » increased release (Expand Search), increased crash (Expand Search)
largest decrease » larger decrease (Expand Search), marked decrease (Expand Search)
linear decrease » linear increase (Expand Search)
increase decrease » increased release (Expand Search), increased crash (Expand Search)
largest decrease » larger decrease (Expand Search), marked decrease (Expand Search)
linear decrease » linear increase (Expand Search)
-
621
-
622
-
623
-
624
-
625
-
626
Scores vs Skip ratios on single-agent task.
Published 2025“…The inferences reduction significantly decreases the time and FLOPs required by the <i>LazyAct</i> algorithm to complete tasks. …”
-
627
Time(s) and GFLOPs savings of single-agent tasks.
Published 2025“…The inferences reduction significantly decreases the time and FLOPs required by the <i>LazyAct</i> algorithm to complete tasks. …”
-
628
The source code of LazyAct.
Published 2025“…The inferences reduction significantly decreases the time and FLOPs required by the <i>LazyAct</i> algorithm to complete tasks. …”
-
629
Win rate vs Skip ratios on multi-agents tasks.
Published 2025“…The inferences reduction significantly decreases the time and FLOPs required by the <i>LazyAct</i> algorithm to complete tasks. …”
-
630
Visualization on SMAC-25m based on <i>LazyAct</i>.
Published 2025“…The inferences reduction significantly decreases the time and FLOPs required by the <i>LazyAct</i> algorithm to complete tasks. …”
-
631
Single agent and multi-agents tasks for <i>LazyAct</i>.
Published 2025“…The inferences reduction significantly decreases the time and FLOPs required by the <i>LazyAct</i> algorithm to complete tasks. …”
-
632
Network architectures for multi-agents task.
Published 2025“…The inferences reduction significantly decreases the time and FLOPs required by the <i>LazyAct</i> algorithm to complete tasks. …”
-
633
-
634
-
635
-
636
-
637
A Locally Linear Dynamic Strategy for Manifold Learning.
Published 2025“…For 10-30% noise, where the Hebbian network employs a local linear transform, learning selectively increases signal direction alignment (blue) while simultaneously decreasing noise direction alignment (orange). …”
-
638
-
639
-
640