MAMBPO: Sample-efficient multi-robot reinforcement learning using learned world models

Daniel Willemsen, Mario Coppola, Guido C.H.E. de Croon

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

11 Citations (Scopus)

Fingerprint

Dive into the research topics of 'MAMBPO: Sample-efficient multi-robot reinforcement learning using learned world models'. Together they form a unique fingerprint.

Computer Science

INIS

Keyphrases

Chemical Engineering