scientific article; zbMATH DE number 3898638
From MaRDI portal
Publication:3677539
[For the entire collection see Zbl 0517.00013.] The author considers a semi-Markov decision process with an unknown parameter (vector) in its kernels. It is required to determine strategies for estimating the unknown parameter and to choose control policies, based on the history of the system, so as to approach the maximum expected average reward. The author proves some convergence results and presents several examples.
Recommendations
- Learning algorithms for Markov decision processes
- AVERAGE-OPTIMAL ADAPTIVE POLICIES IN SEMI-MARKOV DECISION PROCESSES INCLUDING AN UNKNOWN PARAMETER
- A learning algorithm for communicating Markov decision processes with unknown transition matrices
- Solving semi-Markov decision problems using average reward reinforcement learning
- Semi-Markov decision processes with limiting ratio average rewards
Cited in
(8)- Multiaction learning automata possessing ergodicity of the mean
- Recent advances in learning automata
- A sojourn-based approach to semi-Markov reinforcement learning
- A learning algorithm for communicating Markov decision processes with unknown transition matrices
- Solving semi-Markov decision problems using average reward reinforcement learning
- AVERAGE-OPTIMAL ADAPTIVE POLICIES IN SEMI-MARKOV DECISION PROCESSES INCLUDING AN UNKNOWN PARAMETER
- Finite State Automata Resulting from Temporal Information Maximization and a Temporal Learning Rule
- On conditional optimality of a class of learning automata in random environments
This page was built for publication:
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3677539)