A double DRL architecture selects forecasting models dynamically from a committee and introduces average-reward-convergence early stopping, demonstrating robustness on grocery sales and snack demand datasets.
Bidirectional recurrent neural networks.Signal Processing, IEEE Transactions on, 45:2673 – 2681, 12 1997
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Designing a double deep reinforcement learning selection tool for resilient demand prediction
A double DRL architecture selects forecasting models dynamically from a committee and introduces average-reward-convergence early stopping, demonstrating robustness on grocery sales and snack demand datasets.