Login / Signup
On Computing the Fixed-Point Probability Vector of Ergodic Transition Matrices.
Patrick L. Odell
E. P. Decell
Published in:
J. ACM (1967)
Keyphrases
</>
fixed point
transition matrices
policy iteration
markov decision processes
sufficient conditions
floating point
probability distribution
dynamical systems
reinforcement learning
markov chain
fixed point theorem
belief propagation
multi agent
sample path