Learning-Based Mean-Payoff Optimization in an Unknown MDP under Omega-Regular Constraints

TL;DR

This paper develops online learning strategies for unknown MDPs to maximize mean-payoff while satisfying parity constraints, offering guarantees with finite or infinite memory depending on the scenario.

Contribution

It introduces novel online learning strategies for unknown MDPs that balance mean-payoff optimization with parity constraints, with proven guarantees and tight bounds.

Findings

Finite-memory strategies achieve near-optimal mean-payoff with high probability.

Infinite-memory strategies ensure parity objectives surely while optimizing mean-payoff.

Guarantees are proven to be tight, with no stronger guarantees possible in some cases.

Abstract

We formalize the problem of maximizing the mean-payoff value with high probability while satisfying a parity objective in a Markov decision process (MDP) with unknown probabilistic transition function and unknown reward function. Assuming the support of the unknown transition function and a lower bound on the minimal transition probability are known in advance, we show that in MDPs consisting of a single end component, two combinations of guarantees on the parity and mean-payoff objectives can be achieved depending on how much memory one is willing to use. (i) For all $\epsilon$ and $\gamma$ we can construct an online-learning finite-memory strategy that almost-surely satisfies the parity objective and which achieves an $\epsilon$-optimal mean payoff with probability at least $1 - \gamma$. (ii) Alternatively, for all $\epsilon$ and $\gamma$ there exists an online-learning infinite-memory strategy that satisfies the parity objective surely and which achieves an $\epsilon$-optimal mean payoff with probability at least $1 - \gamma$. We extend the above results to MDPs consisting of more than one end component in a natural way. Finally, we show that the aforementioned guarantees are tight, i.e. there are MDPs for which stronger combinations of the guarantees cannot be ensured.