Classic RL agents (Q-learning, SARSA, Expected SARSA) can learn to select among four fixed NoC routing algorithms to maintain near-optimal throughput under changing injection rates and traffic patterns.
Garnet: A detailed on-chip network model inside a full- system simulator
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NI 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reinforcement Learning based Interconnection Routing for Adaptive Traffic Optimization
Classic RL agents (Q-learning, SARSA, Expected SARSA) can learn to select among four fixed NoC routing algorithms to maintain near-optimal throughput under changing injection rates and traffic patterns.