GRASP reduces communication in remote control by 12-fold on average (50-fold for continuous actions) by having actors generate actions via guided sampling and local policy learning instead of receiving full actions or rewards.
Jakob Foerster, Ioannis Alexandros Assael, Nando de Freitas, and Shimon Whiteson
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Remote Action Generation: Remote Control with Minimal Communication
GRASP reduces communication in remote control by 12-fold on average (50-fold for continuous actions) by having actors generate actions via guided sampling and local policy learning instead of receiving full actions or rewards.