Decomposable Markov Decision Processes: A Fluid Optimization Approach
From MaRDI portal
Publication:2957475
DOI10.1287/opre.2016.1531zbMath1354.90164OpenAlexW2530224637MaRDI QIDQ2957475
Velibor V. Mišić, Dimitris J. Bertsimas
Publication date: 26 January 2017
Published in: Operations Research (Search for Journal in Brave)
Full work available at URL: https://semanticscholar.org/paper/522efbe3ae86366f696d5c53e68cc70396b87974
Related Items
Dynamic Programs with Shared Resources and Signals: Dynamic Fluid Policies and Asymptotic Optimality ⋮ Future memories are not needed for large classes of POMDPs ⋮ Group Maintenance: A Restless Bandits Approach ⋮ A Simplex Method for Countably Infinite Linear Programs
Cites Work
- Unnamed Item
- Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
- Duality in infinite dimensional linear programming
- Fast Multiple-Splitting Algorithms for Convex Optimization
- Theory and Applications of Robust Optimization
- Dynamic Bid Prices in Revenue Management
- Relaxations of Weakly Coupled Stochastic Dynamic Programs
- The Linear Programming Approach to Approximate Dynamic Programming
- Characterization and Optimization of Achievable Performance in General Queueing Systems
- A Characterization of Waiting Time Performance Realizable by Single-Server Queues
- Restless Bandits, Linear Programming Relaxations, and a Primal-Dual Index Heuristic
- Conservation Laws, Extended Polymatroids and Multiarmed Bandit Problems; A Polyhedral Approach to Indexable Systems
- Learning to Optimize via Posterior Sampling
- A Linear Programming Approach to Nonstationary Infinite-Horizon Markov Decision Processes
- On Constraint Sampling in the Linear Programming Approach to Approximate Dynamic Programming
This page was built for publication: Decomposable Markov Decision Processes: A Fluid Optimization Approach
