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:2401.04934 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
DAC models fully decentralized cooperative MARL as a context modeling problem, using latent variables for joint policies to fix non-stationarity in value updates and relative overgeneralization in value estimation.
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.
-
Fully Decentralized Cooperative Multi-Agent Reinforcement Learning is A Context Modeling Problem
DAC models fully decentralized cooperative MARL as a context modeling problem, using latent variables for joint policies to fix non-stationarity in value updates and relative overgeneralization in value estimation.