A monotonic 'switch-type' policy network beats MLP policies on sample efficiency and zero-shot generalization in queueing network control tasks.
Approximation theory of the MLP model in neural net- works,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Novel Switch-Type Policy Network for Resource Allocation Problems: Technical Report
A monotonic 'switch-type' policy network beats MLP policies on sample efficiency and zero-shot generalization in queueing network control tasks.