method · first seen 4 Oct 2026
semi-Markov decision process
Also: SMDP, semi-MDP
A decision process in which actions take variable time, generalizing Markov decision processes to temporally extended actions.
Mentions per week
PapersCodeDiscussion
Earliest sources
- On Semi-Markov Suboptimality in Hierarchical Reinforcement LearningPapers · 4 Oct 2026 · Bingyun Liu, Yuheng Jing
- Learning Robot Metareasoning: Adaptive Computation Budgets for Real-Time ControlPapers · 16 Oct 2026 · Lorenzo Magnino, Antonio Marino, Michael Amir, Daigo Shishika, Amanda Prorok
- Efficient Detailed Scheduling of Multiproduct Pipelines using Action-Decoupled Deep Reinforcement LearningPapers · 2 Nov 2026 · Kai Shao, Ling Jian, Liming Liu, Serguey V. Bogomolov, Xinmin Wang
Latest sources
- Efficient Detailed Scheduling of Multiproduct Pipelines using Action-Decoupled Deep Reinforcement LearningPapers · 2 Nov 2026 · Kai Shao, Ling Jian, Liming Liu, Serguey V. Bogomolov, Xinmin Wang
- Learning Robot Metareasoning: Adaptive Computation Budgets for Real-Time ControlPapers · 16 Oct 2026 · Lorenzo Magnino, Antonio Marino, Michael Amir, Daigo Shishika, Amanda Prorok
- On Semi-Markov Suboptimality in Hierarchical Reinforcement LearningPapers · 4 Oct 2026 · Bingyun Liu, Yuheng Jing