Kolnogorov Alexander Valerianovich

Publications in Math-Net.Ru

1. A limiting description of control in a gaussian one-armed bandit problem
   
   J. Comp. Eng. Math., 12:1 (2025),  11–22
2. Minimax approach to the Gaussian multi-armed bandit
   
   Trudy Inst. Mat. i Mekh. UrO RAN, 31:3 (2025),  150–166
3. A limiting description in a Gaussian one-armed bandit problem with both unknown parameters
   
   Vestnik YuUrGU. Ser. Mat. Model. Progr., 18:1 (2025),  35–45
4. Invariant description of control in a Gaussian one-armed bandit problem
   
   Vestnik YuUrGU. Ser. Mat. Model. Progr., 17:1 (2024),  27–36
5. Optimization of two-alternative batch processing with parameter estimation based on data inside batches
   
   J. Comp. Eng. Math., 10:4 (2023),  40–50
6. UCB strategies and optimization of batch processing in a one-armed bandit problem
   
   Mat. Teor. Igr Pril., 15:4 (2023),  3–27
7. Customization of J. Bather UCB strategy for a Gaussian multi-armed bandit
   
   Mat. Teor. Igr Pril., 14:2 (2022),  3–30
8. Poissonian two-armed bandit: a new approach
   
   Probl. Peredachi Inf., 58:2 (2022),  66–91
9. Gaussian one-armed bandit with both unknown parameters
   
   Sib. Èlektron. Mat. Izv., 19:2 (2022),  639–650
10. Two-armed bandit problem and batch version of the mirror descent algorithm
    
    Mat. Teor. Igr Pril., 13:2 (2021),  9–39
11. Gaussian two-armed bandit: limiting description
    
    Probl. Peredachi Inf., 56:3 (2020),  86–111
12. Gaussian two-armed bandit and optimization of batch data processing
    
    Probl. Peredachi Inf., 54:1 (2018),  93–111
13. On a limiting description of robust parallel control in a random environment
    
    Avtomat. i Telemekh., 2015, no. 7,  111–126
14. One-armed bandit problem for parallel data processing systems
    
    Probl. Peredachi Inf., 51:2 (2015),  99–113
15. Robust parallel control in a random environment and data processing optimization
    
    Avtomat. i Telemekh., 2014, no. 12,  42–55
16. Parallel design of robust control in the stochastic environment (the two-armed bandit problem)
    
    Avtomat. i Telemekh., 2012, no. 4,  114–130
17. Two-armed bandit problem for parallel data processing systems
    
    Probl. Peredachi Inf., 48:1 (2012),  83–95
18. Finding minimax strategy and minimax risk in a random environment (the two-armed bandit problem)
    
    Avtomat. i Telemekh., 2011, no. 5,  127–138
19. Reasonable control of the average level of random noise
    
    Avtomat. i Telemekh., 2000, no. 1,  70–80
20. On Optimal Prior Learning Time in the Two-Armed Bandit Problem
    
    Probl. Peredachi Inf., 36:4 (2000),  117–127
21. A simple behavioral strategy in a stationary environment with a guaranteed power rate of convergence
    
    Avtomat. i Telemekh., 1999, no. 8,  95–101
22. On Optimal Behavior of Finite Automata in a Random Medium
    
    Probl. Peredachi Inf., 34:1 (1998),  77–86
23. On the justification of two heuristic methods in the problem of appropriate behavior in a stationary environment
    
    Avtomat. i Telemekh., 1992, no. 8,  83–85
24. On a behavior strategy in a stationary medium with an unimprovable guaranteed estimate of the convergence of mean income
    
    Avtomat. i Telemekh., 1991, no. 5,  183–186
25. Томата, asymptotically optimal in a stationary environment and having growing memory
    
    Avtomat. i Telemekh., 1984, no. 9,  129–137
26. Asymptotically optimal automata with growing memory
    
    Dokl. Akad. Nauk SSSR, 270:3 (1983),  562–564