Adaptive control of Markov processes with incomplete state information and unknown parameters (Q1071659)
From MaRDI portal
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Adaptive control of Markov processes with incomplete state information and unknown parameters |
scientific article |
Statements
Adaptive control of Markov processes with incomplete state information and unknown parameters (English)
0 references
1987
0 references
Recent results for parameter-adaptive Markov decision processes (MDP's) are extended to partially observed MDP's depending on unknown parameters. These results include approximations converging uniformly to the optimal reward function and asymptotically optimal adaptive policies.
0 references
unknown parameters
0 references
approximations
0 references
optimal reward function
0 references
asymptotically optimal adaptive policies
0 references
partially observed Markov decision processes
0 references
discounted reward criterion
0 references
nonstationary value iteration
0 references
principle of estimation and control
0 references
0 references
0 references
0 references
0 references
