mlsanityData to 14 Oct 2026

Neural Stochastic Dual Dynamic Programming

arXiv 2112.00874 ↗First posted 1 Dec 2021cs.LG stat.MLcited by 6

Not on the map. Why?

Abstract (arXiv)

Stochastic dual dynamic programming (SDDP) is a state-of-the-art method for solving multi-stage stochastic optimization, widely used for modeling real-world process optimization tasks. Unfortunately, SDDP has a worst-case complexity that scales exponentially in the number of decision variables, which severely limits applicability to only low dimensional problems. To overcome this limitation, we extend SDDP by introducing a trainable neural model that learns to map problem instances to a piece-wise linear value function within intrinsic low-dimension space, which is architected specifically to interact with a base SDDP solver, so that can accelerate optimization performance on new instances. The proposed Neural Stochastic Dual Dynamic Programming (nu-SDDP) continually self-improves by solving successive problems. An empirical investigation demonstrates that nu-SDDP can significantly reduce problem solving cost without sacrificing solution quality over competitors such as SDDP and reinforcement learning algorithms, across a range of synthetic and real-world process optimization problems.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 19 of its 58 references that are in the map. First posted on arXiv 1 Dec 2021.

Builds on

19 of 58 references.

References · 19

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  4. 2015Continuous control with deep reinforcement learningcited by 3,407
  5. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  6. 2017Learning Combinatorial Optimization Algorithms over Graphscited by 561
  7. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 389
  8. 2014From Predictive to Prescriptive Analyticscited by 143
  9. 2019Meta-Q-Learningcited by 62
  10. 2020OR-Gym: A Reinforcement Learning Library for Operations Research Problemscited by 51
  11. 2016Applying Deep Learning to the Newsvendor Problemcited by 24
  12. 2019ORL: Reinforcement Learning Benchmarks for Online Stochastic Optimization Problemscited by 21
7 more
  1. 2019Learning to Plan in High Dimensions via Neural Exploration-Exploitation Treescited by 18
  2. 2019Meta Reinforcement Learning with Task Embedding and Shared Policycited by 15
  3. 2018VPE: Variational Policy Embedding for Transfer Reinforcement Learningcited by 8
  4. 2015Scale Up Nonlinear Component Analysis with Doubly Stochastic Gradientscited by 6
  5. 2017Dynamic Stochastic Approximation for Multi-stage Stochastic Optimizationcited by 3
  6. 2019Complexity of Stochastic Dual Dynamic Programmingcited by 2
  7. 2020Randomized Progressive Hedging methods for Multi-stage Stochastic Programmingcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 1; 2024: 1; 2025: 1.

6 papers.

  1. 2022Neur2SP: Neural Two-Stage Stochastic Programmingcited by 17
  2. 2022Fast Continuous and Integer L-shaped Heuristics Through Supervised Learningcited by 6
  3. 2022Learning to Optimize with Stochastic Dominance Constraintscited by 5
  4. 2025ICNN-enhanced 2SP: Leveraging input convex neural networks for solving two-stage stochastic programmingcited by 3
  5. 2023Business Metric-Aware Forecasting for Inventory Managementcited by 1
  6. 2024Transformer-based Stagewise Decomposition for Large-Scale Multistage Stochastic Optimizationcited by 0