Name
Title | ||
|---|---|---|
Learning-Based Mean-Payoff Optimization in an Unknown MDP under Omega-Regular Constraints. |
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. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.4230/LIPIcs.CONCUR.2018.8 | CONCUR |
DocType | Volume | Citations |
Conference | abs/1804.08924 | 0 |
PageRank | References | Authors |
0.34 | 6 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jan Kretínský | 1 | 159 | 16.02 |
| Guillermo A. Pérez | 2 | 24 | 3.52 |
| Jean-François Raskin | 3 | 1735 | 100.15 |