Reconstructing Model Parameters in Partially-Observable Discrete Stochastic Systems.

Robert Buchholz Claudia Krull Graham Horton

Published in: ASMTA (2011)

Keyphrases

partially observable
stochastic systems
reinforcement learning
markov decision processes
dynamical systems
decision problems
state space
infinite horizon
stochastic models
sample path
confidence intervals
optimal policy
belief state
reward function
optimal control
chaotic systems
asymptotic analysis
decision making