COOPER is a distributed MARL method that learns emergent reputation assessment rules and policies from rewards, shown on donation and coin games in grid worlds with adaptation across co-players and networks.
arXiv preprint arXiv:2103.13333 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning to cooperate with emergent reputation via multi-agent reinforcement learning
COOPER is a distributed MARL method that learns emergent reputation assessment rules and policies from rewards, shown on donation and coin games in grid worlds with adaptation across co-players and networks.