Search

• < Previous
• 1
• Next >

Strategy Complexity of Point Payoff, Mean Payoff and Total Payoff Objectives in Countable MDPs

We study countably infinite Markov decision processes (MDPs) with real-valued transition rewards. Every infinite run induces the following sequences of payoffs: 1. Point payoff (the sequence of directly seen transition rewards), 2. Mean payoff (the sequence of the sums of all rewards so far, divided&nbsp;[&hellip;]