@misc{5434, abstract = {DEC-POMDPs extend POMDPs to a multi-agent setting, where several agents operate in an uncertain environment independently to achieve a joint objective. DEC-POMDPs have been studied with finite-horizon and infinite-horizon discounted-sum objectives, and there exist solvers both for exact and approximate solutions. In this work we consider Goal-DEC-POMDPs, where given a set of target states, the objective is to ensure that the target set is reached with minimal cost. We consider the indefinite-horizon (infinite-horizon with either discounted-sum, or undiscounted-sum, where absorbing goal states have zero-cost) problem. We present a new method to solve the problem that extends methods for finite-horizon DEC- POMDPs and the RTDP-Bel approach for POMDPs. We present experimental results on several examples, and show our approach presents promising results.}, author = {Anonymous, 1 and Anonymous, 2}, issn = {2664-1690}, pages = {16}, publisher = {IST Austria}, title = {{Optimal cost indefinite-horizon reachability in goal DEC-POMDPs}}, year = {2015}, } @inproceedings{1657, abstract = {We consider Markov decision processes (MDPs) with multiple limit-average (or mean-payoff) objectives. There exist two different views: (i) ~the expectation semantics, where the goal is to optimize the expected mean-payoff objective, and (ii) ~the satisfaction semantics, where the goal is to maximize the probability of runs such that the mean-payoff value stays above a given vector. We consider optimization with respect to both objectives at once, thus unifying the existing semantics. Precisely, the goal is to optimize the expectation while ensuring the satisfaction constraint. Our problem captures the notion of optimization with respect to strategies that are risk-averse (i.e., Ensure certain probabilistic guarantee). Our main results are as follows: First, we present algorithms for the decision problems, which are always polynomial in the size of the MDP. We also show that an approximation of the Pareto curve can be computed in time polynomial in the size of the MDP, and the approximation factor, but exponential in the number of dimensions. Second, we present a complete characterization of the strategy complexity (in terms of memory bounds and randomization) required to solve our problem. }, author = {Chatterjee, Krishnendu and Komárková, Zuzana and Kretinsky, Jan}, location = {Kyoto, Japan}, pages = {244 -- 256}, publisher = {IEEE}, title = {{Unifying two views on multiple mean-payoff objectives in Markov decision processes}}, doi = {10.1109/LICS.2015.32}, year = {2015}, } @inproceedings{1656, abstract = {Recently there has been a significant effort to handle quantitative properties in formal verification and synthesis. While weighted automata over finite and infinite words provide a natural and flexible framework to express quantitative properties, perhaps surprisingly, some basic system properties such as average response time cannot be expressed using weighted automata, nor in any other know decidable formalism. In this work, we introduce nested weighted automata as a natural extension of weighted automata which makes it possible to express important quantitative properties such as average response time. In nested weighted automata, a master automaton spins off and collects results from weighted slave automata, each of which computes a quantity along a finite portion of an infinite word. Nested weighted automata can be viewed as the quantitative analogue of monitor automata, which are used in run-time verification. We establish an almost complete decidability picture for the basic decision problems about nested weighted automata, and illustrate their applicability in several domains. In particular, nested weighted automata can be used to decide average response time properties.}, author = {Chatterjee, Krishnendu and Henzinger, Thomas A and Otop, Jan}, booktitle = {Proceedings - Symposium on Logic in Computer Science}, location = {Kyoto, Japan}, publisher = {IEEE}, title = {{Nested weighted automata}}, doi = {10.1109/LICS.2015.72}, volume = {2015-July}, year = {2015}, } @misc{5429, abstract = {We consider Markov decision processes (MDPs) with multiple limit-average (or mean-payoff) objectives. There have been two different views: (i) the expectation semantics, where the goal is to optimize the expected mean-payoff objective, and (ii) the satisfaction semantics, where the goal is to maximize the probability of runs such that the mean-payoff value stays above a given vector. We consider the problem where the goal is to optimize the expectation under the constraint that the satisfaction semantics is ensured, and thus consider a generalization that unifies the existing semantics. Our problem captures the notion of optimization with respect to strategies that are risk-averse (i.e., ensures certain probabilistic guarantee). Our main results are algorithms for the decision problem which are always polynomial in the size of the MDP. We also show that an approximation of the Pareto-curve can be computed in time polynomial in the size of the MDP, and the approximation factor, but exponential in the number of dimensions. Finally, we present a complete characterization of the strategy complexity (in terms of memory bounds and randomization) required to solve our problem.}, author = {Chatterjee, Krishnendu and Komarkova, Zuzana and Kretinsky, Jan}, issn = {2664-1690}, pages = {41}, publisher = {IST Austria}, title = {{Unifying two views on multiple mean-payoff objectives in Markov decision processes}}, doi = {10.15479/AT:IST-2015-318-v1-1}, year = {2015}, } @misc{5435, abstract = {We consider Markov decision processes (MDPs) with multiple limit-average (or mean-payoff) objectives. There have been two different views: (i) the expectation semantics, where the goal is to optimize the expected mean-payoff objective, and (ii) the satisfaction semantics, where the goal is to maximize the probability of runs such that the mean-payoff value stays above a given vector. We consider the problem where the goal is to optimize the expectation under the constraint that the satisfaction semantics is ensured, and thus consider a generalization that unifies the existing semantics. Our problem captures the notion of optimization with respect to strategies that are risk-averse (i.e., ensures certain probabilistic guarantee). Our main results are algorithms for the decision problem which are always polynomial in the size of the MDP. We also show that an approximation of the Pareto-curve can be computed in time polynomial in the size of the MDP, and the approximation factor, but exponential in the number of dimensions. Finally, we present a complete characterization of the strategy complexity (in terms of memory bounds and randomization) required to solve our problem.}, author = {Chatterjee, Krishnendu and Komarkova, Zuzana and Kretinsky, Jan}, issn = {2664-1690}, pages = {51}, publisher = {IST Austria}, title = {{Unifying two views on multiple mean-payoff objectives in Markov decision processes}}, doi = {10.15479/AT:IST-2015-318-v2-1}, year = {2015}, }