NONPARAMETRIC BANDIT METHODS.
- Published in:
- Annals of Operations Research, 1991, v. 28, n. 1-4, p. 297, doi. 10.1007/BF02055587
- By:
- Publication type:
- Article
Works matching IS 02545330 AND DT 1991 AND VI 28 AND IP 1-4
Results: 17
1
2
THE EXISTENCE OF SENSITIVE OPTIMAL POLICIES IN TWO MULTI-DIMENSIONAL QUEUEING MODELS.
- Published in:
- Annals of Operations Research, 1991, v. 28, n. 1-4, p. 273, doi. 10.1007/BF02055586
- By:
- Publication type:
- Article
3
VALUE ITERATION IN COUNTABLE STATE AVERAGE COST MARKOV DECISION PROCESSES WITH UNBOUNDED COSTS.
- Published in:
- Annals of Operations Research, 1991, v. 28, n. 1-4, p. 261, doi. 10.1007/BF02055585
- By:
- Publication type:
- Article
4
OPTIMAL ADMISSION POLICIES FOR A FINITE QUEUE WITH BURSTY ARRIVALS.
- Published in:
- Annals of Operations Research, 1991, v. 28, n. 1-4, p. 243, doi. 10.1007/BF02055584
- By:
- Publication type:
- Article
5
AN IMPROVED ALGORITHM FOR SOLVING COMMUNICATING AVERAGE REWARD MARKOV DECISION PROCESSES.
- Published in:
- Annals of Operations Research, 1991, v. 28, n. 1-4, p. 229, doi. 10.1007/BF02055583
- By:
- Publication type:
- Article
6
ERROR BOUND FOR THE DYNAMIC LOT SIZE MODEL WITH BACKLOGGING.
- Published in:
- Annals of Operations Research, 1991, v. 28, n. 1-4, p. 213, doi. 10.1007/BF02055582
- By:
- Publication type:
- Article
7
DENUMERABLE SEMI-MARKOV DECISION CHAINS WITH SMALL INTEREST RATES.
- Published in:
- Annals of Operations Research, 1991, v. 28, n. 1-4, p. 185, doi. 10.1007/BF02055581
- By:
- Publication type:
- Article
8
NONPARAMETRIC ESTIMATION AND ADAPTIVE CONTROL IN A CLASS OF FINITE MARKOV DECISION CHAINS.
- Published in:
- Annals of Operations Research, 1991, v. 28, n. 1-4, p. 169, doi. 10.1007/BF02055580
- By:
- Publication type:
- Article
9
SINGULARLY PERTURBED MARKOV CONTROL PROBLEM: LIMITING AVERAGE COST.
- Published in:
- Annals of Operations Research, 1991, v. 28, n. 1-4, p. 153, doi. 10.1007/BF02055579
- By:
- Publication type:
- Article
10
TWO-PERSON ZERO-SUM STOCHASTIC GAMES.
- Published in:
- Annals of Operations Research, 1991, v. 28, n. 1-4, p. 135, doi. 10.1007/BF02055578
- By:
- Publication type:
- Article
11
ADAPTIVE CONTROL OF CONSTRAINED MARKOV CHAINS: CRITERIA AND POLICIES.
- Published in:
- Annals of Operations Research, 1991, v. 28, n. 1-4, p. 101, doi. 10.1007/BF02055577
- By:
- Publication type:
- Article
12
ON THE CONSTRUCTION OF ε-OPTIMAL STRATEGIES IN PARTIALLY OBSERVED MDPs.
- Published in:
- Annals of Operations Research, 1991, v. 28, n. 1-4, p. 81, doi. 10.1007/BF02055576
- By:
- Publication type:
- Article
13
TWO EXTENSIONS OF ASYMPTOTIC METHODS IN CONTROLLED MARKOV CHAINS.
- Published in:
- Annals of Operations Research, 1991, v. 28, n. 1-4, p. 67, doi. 10.1007/BF02055575
- By:
- Publication type:
- Article
14
A SURVEY OF ALGORITHMIC METHODS FOR PARTIALLY OBSERVED MARKOV DECISION PROCESSES.
- Published in:
- Annals of Operations Research, 1991, v. 28, n. 1-4, p. 47, doi. 10.1007/BF02055574
- By:
- Publication type:
- Article
15
RECURRENCE CONDITIONS FOR MARKOV DECISION PROCESSES WITH BOREL STATE SPACE: A SURVEY.
- Published in:
- Annals of Operations Research, 1991, v. 28, n. 1-4, p. 29
- By:
- Publication type:
- Article
16
RECENT RESULTS ON CONDITIONS FOR THE EXISTENCE OF AVERAGE OPTIMAL STATIONARY POLICIES.
- Published in:
- Annals of Operations Research, 1991, v. 28, n. 1-4, p. 3, doi. 10.1007/BF02055572
- By:
- Publication type:
- Article
17
PREFACE.
- Published in:
- 1991
- By:
- Publication type:
- Book Chapter