## Found 5,344 Documents (Results 1–100)

100
MathJax

MSC:  90Bxx
Full Text:

Full Text:

MSC:  68Txx
Full Text:

### Mean-field Markov decision processes with common noise and open-loop controls. (English)Zbl 07522878

MSC:  90C40 49L20
Full Text:

### A note on optimization formulations of Markov decision processes. (English)Zbl 07512733

MSC:  60J10 60J22 90C05
Full Text:

### Constrained discounted stochastic games. (English)Zbl 07511777

MSC:  91A15 91A10 90C40
Full Text:

Full Text:

### Variable demand and multi-commodity flow in Markovian network equilibrium. (English)Zbl 07507287

MSC:  91A43 90C40 90B15
Full Text:

### LP based upper and lower bounds for Cesàro and Abel limits of the optimal values in problems of control of stochastic discrete time systems. (English)Zbl 07496956

MSC:  90Cxx 93Exx 60Jxx
Full Text:

Full Text:

### Process-based risk measures and risk-averse control of discrete-time systems. (English)Zbl 07495384

MSC:  90C15 90C39 90C40
Full Text:

Full Text:

MSC:  90Bxx
Full Text:

### A step-by-step tutorial on active inference and its application to empirical data. (English)Zbl 07490888

MSC:  91E10 91E30 90C40
Full Text:

### Multi-objective dynamic programming with limited precision. (English)Zbl 07489941

MSC:  90C29 90C40 90C39
Full Text:

MSC:  90-XX
Full Text:

MSC:  90-XX
Full Text:

### Multiply accelerated value iteration for nonsymmetric affine fixed point problems and application to Markov decision processes. (English)Zbl 07487114

MSC:  90C39 90C40 47H09
Full Text:

### Risk-sensitive semi-Markov decision problems with discounted cost and general utilities. (English)Zbl 1480.90248

MSC:  90C40 93E20
Full Text:

### A restless bandit model for resource allocation, competition, and reservation. (English)Zbl 07476285

MSC:  91B32 91B70 90C40
Full Text:

### Optimal sequential multiclass diagnosis. (English)Zbl 1482.90111

MSC:  90B50 90C40
Full Text:

### On the equivalence of the integral and differential Bellman equations in impulse control problems. (English)Zbl 1482.49038

MSC:  49N25 49L20 90C40
Full Text:

MSC:  90C40
Full Text:

### Learning to scan: a deep reinforcement learning approach for personalized scanning in CT imaging. (English)Zbl 1482.92044

MSC:  92C55 68T07 90C40
Full Text:

MSC:  90C40
Full Text:

Full Text:

Full Text:

MSC:  90C40
Full Text:

### Convergence problem of a sequence of first passage Markov decision processes with varying discount factors. (Chinese. English summary)Zbl 07524828

MSC:  60J10 90C40 93E20
Full Text:

Full Text:

### Fast and asymptotic steering to a steady state for networks flows. (English)Zbl 07495287

Nielsen, Frank (ed.) et al., Geometric science of information. 5th international conference, GSI 2021, Paris, France, July 21–23, 2021. Proceedings. Cham: Springer. Lect. Notes Comput. Sci. 12829, 860-868 (2021).
Full Text:

### On the computational efficiency of catalyst accelerated coordinate descent. (English)Zbl 07495079

Pardalos, Panos (ed.) et al., Mathematical optimization theory and operations research. 20th international conference, MOTOR 2021, Irkutsk, Russia, July 5–10, 2021. Proceedings. Cham: Springer. Lect. Notes Comput. Sci. 12755, 176-191 (2021).
MSC:  90C25 90C40
Full Text:

### Timing it right: balancing inpatient congestion vs. readmission risk at discharge. (English)Zbl 1482.90107

MSC:  90B50 90C40 90C59
Full Text:

### Envelope theorems for multistage linear stochastic optimization. (English)Zbl 07474574

MSC:  90C15 90C40
Full Text:

### Optimal control of partially observable semi-Markovian failing systems: an analysis using a phase methodology. (English)Zbl 1482.90081

MSC:  90B25 60G40 90C40
Full Text:

### A diffusion wavelets-based multiscale framework for inverse optimal control of stochastic systems. (English)Zbl 1483.93705

MSC:  93E20 49N45 90C40
Full Text:

### Controlling a random population. (English)Zbl 07471672

MSC:  03B70 68-XX
Full Text:

Full Text:

MSC:  68Txx
Full Text:

MSC:  68Txx
Full Text:

### A Moreau-Yosida regularization for Markov decision processes. (English)Zbl 1478.90142

MSC:  90C40 49M20
Full Text:

Full Text:

### Optimal routing control of a retrial queue with two-phase service. (English)Zbl 1482.90064

MSC:  90B22 90C40
Full Text:

Full Text:

Full Text:

MSC:  90C40
Full Text:

### A general theory of multiarmed bandit processes with constrained arm switches. (English)Zbl 1483.90092

MSC:  90C15 90C40
Full Text:

Full Text:

Full Text:

### Dynamic equilibrium with randomly arriving players. (English)Zbl 1480.91012

MSC:  91A11 90C39 90C40
Full Text:

### Compositional abstraction-based synthesis of general MDPs via approximate probabilistic relations. (English)Zbl 1478.93665

MSC:  93E03 90C40 93C10
Full Text:

MSC:  68T37
Full Text:

### Special subclass of generalized semi-Markov decision processes with discrete time. (English)Zbl 1481.90307

Gentile, Claudio (ed.) et al., Graphs and combinatorial optimization: from theory to applications. Proceedings of the 18th Cologne-Twente workshop on graphs and combinatorial optimization (CTW2020), online, September 14–16, 2020. Cham: Springer. AIRO Springer Ser. 5, 375-386 (2021).
MSC:  90C40
Full Text:

### Randomness and elements of decision theory applied to signals. (English)Zbl 1479.94001

Cham: Springer (ISBN 978-3-030-90313-8/hbk; 978-3-030-90316-9/pbk; 978-3-030-90314-5/ebook). xvii, 242 p. (2021).
Full Text:

Full Text:

Full Text:

Full Text:

Full Text:

Full Text:

### On the convergence of reinforcement learning with Monte Carlo exploring starts. (English)Zbl 1478.93667

MSC:  93E03 68T05 90C40
Full Text:

### Supervisor synthesis of POMDP via automata learning. (English)Zbl 1478.93191

MSC:  93B50 90C40
Full Text:

### Optimal control of production time of perishable inventory system with postponed demands. (English)Zbl 1482.90023

MSC:  90B05 90C40
Full Text:

### An approximate dynamic programming approach to project scheduling with uncertain resource availabilities. (English)Zbl 1481.90194

MSC:  90B36 90C39 90C40
Full Text:

Full Text:

### Cooperative and non-cooperative behaviour in the exploitation of a common renewable resource with environmental stochasticity. (English)Zbl 1481.91139

MSC:  91B76 90C40
Full Text:

### Equilibrium in misspecified Markov decision processes. (English)Zbl 1475.91181

MSC:  91B52 90C40
Full Text:

### Prospect-theoretic Q-learning. (English)Zbl 07423717

MSC:  68Txx 90C40
Full Text:

MSC:  90Bxx
Full Text:

Full Text:

### Stochastic control of a micro-grid using battery energy storage in solar-powered buildings. (English)Zbl 1480.90249

MSC:  90C40 90C90
Full Text:

Full Text:

### Minimizing spectral risk measures applied to Markov decision processes. (English)Zbl 1479.90209

MSC:  90C40 91G70 91G05
Full Text:

Full Text:

Full Text:

Full Text:

### Convergence of value functions for finite horizon Markov decision processes with constraints. (English)Zbl 1472.93197

MSC:  93E20 60J10 90C40
Full Text:

### Time-inconsistent risk-sensitive equilibrium for countable-stated Markov decision processes. (English)Zbl 1478.49023

MSC:  49L20 60J10
Full Text:

MSC:  68Txx
Full Text:

### On an approach to evaluation of health care programme by Markov decision model. (English)Zbl 1471.92156

Piunovskiy, Alexey (ed.) et al., Modern trends in controlled stochastic processes: theory and applications, V.III. Selected papers based on the presentations at the traditional Liverpool workshop on controlled stochastic processes, Liverpool, UK, July 2021. Cham: Springer. Emerg. Complex. Comput. 41, 341-354 (2021).
MSC:  92C50 90C40
Full Text:

### On finite approximations to Markov decision processes with recursive and nonlinear discounting. (English)Zbl 1478.90140

Piunovskiy, Alexey (ed.) et al., Modern trends in controlled stochastic processes: theory and applications, V.III. Selected papers based on the presentations at the traditional Liverpool workshop on controlled stochastic processes, Liverpool, UK, July 2021. Cham: Springer. Emerg. Complex. Comput. 41, 221-247 (2021).
MSC:  90C40 90C59
Full Text:

### Full gradient DQN reinforcement learning: a provably convergent scheme. (English)Zbl 1471.93287

Piunovskiy, Alexey (ed.) et al., Modern trends in controlled stochastic processes: theory and applications, V.III. Selected papers based on the presentations at the traditional Liverpool workshop on controlled stochastic processes, Liverpool, UK, July 2021. Cham: Springer. Emerg. Complex. Comput. 41, 192-220 (2021).
MSC:  93E35 90C40 68T07
Full Text:

### Robustness to approximations and model learning in MDPs and POMDPs. (English)Zbl 1471.93255

Piunovskiy, Alexey (ed.) et al., Modern trends in controlled stochastic processes: theory and applications, V.III. Selected papers based on the presentations at the traditional Liverpool workshop on controlled stochastic processes, Liverpool, UK, July 2021. Cham: Springer. Emerg. Complex. Comput. 41, 166-191 (2021).
MSC:  93E03 93B35 90C40
Full Text:

### Q-learning for distributionally robust Markov decision processes. (English)Zbl 1478.90138

Piunovskiy, Alexey (ed.) et al., Modern trends in controlled stochastic processes: theory and applications, V.III. Selected papers based on the presentations at the traditional Liverpool workshop on controlled stochastic processes, Liverpool, UK, July 2021. Cham: Springer. Emerg. Complex. Comput. 41, 108-128 (2021).
MSC:  90C40
Full Text:

### Controlled random walk: conjecture and counter-example. (English)Zbl 1478.90143

Piunovskiy, Alexey (ed.) et al., Modern trends in controlled stochastic processes: theory and applications, V.III. Selected papers based on the presentations at the traditional Liverpool workshop on controlled stochastic processes, Liverpool, UK, July 2021. Cham: Springer. Emerg. Complex. Comput. 41, 38-56 (2021).
MSC:  90C40 60G50
Full Text:

### First passage exponential optimality problem for semi-Markov decision processes. (English)Zbl 1471.93279

Piunovskiy, Alexey (ed.) et al., Modern trends in controlled stochastic processes: theory and applications, V.III. Selected papers based on the presentations at the traditional Liverpool workshop on controlled stochastic processes, Liverpool, UK, July 2021. Cham: Springer. Emerg. Complex. Comput. 41, 19-37 (2021).
MSC:  93E20 90C40
Full Text:

### Average cost Markov decision processes with semi-uniform Feller transition probabilities. (English)Zbl 1478.90141

Piunovskiy, Alexey (ed.) et al., Modern trends in controlled stochastic processes: theory and applications, V.III. Selected papers based on the presentations at the traditional Liverpool workshop on controlled stochastic processes, Liverpool, UK, July 2021. Cham: Springer. Emerg. Complex. Comput. 41, 1-18 (2021).
MSC:  90C40
Full Text:

### Hybrid control for learning motor skills. (English)Zbl 1471.93184

Lavalle, Steven M. (ed.) et al., Algorithmic foundations of robotics XIV. Proceedings of the fourteenth workshop on the algorithmic foundations of robotics. Cham: Springer. Springer Proc. Adv. Robot. 17, 450-466 (2021).
MSC:  93C85 93E20 90C40
Full Text:

### Imitation learning as $$f$$-divergence minimization. (English)Zbl 1469.68090

Lavalle, Steven M. (ed.) et al., Algorithmic foundations of robotics XIV. Proceedings of the fourteenth workshop on the algorithmic foundations of robotics. Cham: Springer. Springer Proc. Adv. Robot. 17, 313-329 (2021).
MSC:  68T05 90C40 94A17
Full Text:

### Constrained optimality problem of Markov decision processes with Borel spaces and varying discount factors. (English)Zbl 07396268

MSC:  90C40 60J27
Full Text:

### Risk probability optimization problem for finite horizon continuous time Markov decision processes with loss rate. (English)Zbl 07396267

MSC:  93E20 90C40
Full Text:

MSC:  68-XX
Full Text:

### Stochastic policy gradient ascent in reproducing kernel Hilbert spaces. (English)Zbl 1471.93259

MSC:  93E03 93C25 90C40
Full Text:

### Optimal strategies for a fishery model applied to utility functions. (English)Zbl 1471.91351

MSC:  91B76 91B16
Full Text:

### Learning chordal extensions. (English)Zbl 1475.90084

MSC:  90C27 90C40
Full Text:

### Optimal stopping time on discounted semi-Markov processes. (English)Zbl 1473.90174

MSC:  90C40 93E20 60G40
Full Text:

### Multi-objective optimization of long-run average and total rewards. (English)Zbl 1467.68094

Groote, Jan Friso (ed.) et al., Tools and algorithms for the construction and analysis of systems. 27th international conference, TACAS 2021, held as part of the European joint conferences on theory and practice of software, ETAPS 2021, Luxembourg City, Luxembourg, March 27 – April 1, 2021. Proceedings. Part I. Cham: Springer. Lect. Notes Comput. Sci. 12651, 230-249 (2021).
Full Text:

MSC:  90C40
Full Text:

### Points gained in football: using Markov process-based value functions to assess team performance. (English)Zbl 1472.90151

MSC:  90C40 90C90
Full Text:

### Dynamic admission quota control with controllable and uncontrollable demands and random service time. (English)Zbl 1479.90210

MSC:  90C40 90C90
Full Text:

Full Text:

all top 5

all top 5

all top 5

all top 3

all top 3

all top 3