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

Jan Kretínský, Guillermo A. Pérez, Jean-François Raskin, Michael Wagner
2018 International Conference on Concurrency Theory  
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
more » ... e achieved depending on how much memory one is willing to use. (i) For all ε and γ we can construct an online-learning finite-memory strategy that almost-surely satisfies the parity objective and which achieves an ε-optimal mean payoff with probability at least 1 − γ. (ii) Alternatively, for all ε and γ there exists an online-learning infinite-memory strategy that satisfies the parity objective surely and which achieves an ε-optimal mean payoff with probability at least 1 − γ. 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.
doi:10.4230/lipics.concur.2018.8 dblp:conf/concur/KretinskyPR18 fatcat:j6fszayujnd4rku6wa4o4puux4