Proves that independent multi-agent Q-learning for cooperative traffic signal control converges under stated conditions by extending single-agent asynchronous value iteration proofs via stochastic approximation.
Kushner and Dean S
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Convergence of Multiagent Learning Systems for Traffic control
Proves that independent multi-agent Q-learning for cooperative traffic signal control converges under stated conditions by extending single-agent asynchronous value iteration proofs via stochastic approximation.