Papers by Prasenjit Mondal
We prove that a finite (state and action spaces) semi-Markov decision process with limiting ratio... more We prove that a finite (state and action spaces) semi-Markov decision process with limiting ratio average (undiscounted) payoff has an optimal pure semi-stationary policy (i.e., a semi-Markov policy independent of decision epoch count). We conclude by showing (with the aid of a simple example) that the result cannot be strengthened further. A generalized semi-Markov replacement model is proposed that fits in perfectly with such processes and an explicit algorithm is given to compute an optimal pure semi-stationary policy.
Uploads
Papers by Prasenjit Mondal