@inproceedings{79,
abstract = {Markov Decision Processes (MDPs) are a popular class of models suitable for solving control decision problems in probabilistic reactive systems. We consider parametric MDPs (pMDPs) that include parameters in some of the transition probabilities to account for stochastic uncertainties of the environment such as noise or input disturbances. We study pMDPs with reachability objectives where the parameter values are unknown and impossible to measure directly during execution, but there is a probability distribution known over the parameter values. We study for the first time computing parameter-independent strategies that are expectation optimal, i.e., optimize the expected reachability probability under the probability distribution over the parameters. We present an encoding of our problem to partially observable MDPs (POMDPs), i.e., a reduction of our problem to computing optimal strategies in POMDPs. We evaluate our method experimentally on several benchmarks: a motivating (repeated) learner model; a series of benchmarks of varying configurations of a robot moving on a grid; and a consensus protocol.},
author = {Arming, Sebastian and Bartocci, Ezio and Chatterjee, Krishnendu and Katoen, Joost P and Sokolova, Ana},
location = {Beijing, China},
pages = {53--70},
publisher = {Springer},
title = {{Parameter-independent strategies for pMDPs via POMDPs}},
doi = {10.1007/978-3-319-99154-2_4},
volume = {11024},
year = {2018},
}
@article{738,
abstract = {This paper is devoted to automatic competitive analysis of real-time scheduling algorithms for firm-deadline tasksets, where only completed tasks con- tribute some utility to the system. Given such a taskset T , the competitive ratio of an on-line scheduling algorithm A for T is the worst-case utility ratio of A over the utility achieved by a clairvoyant algorithm. We leverage the theory of quantitative graph games to address the competitive analysis and competitive synthesis problems. For the competitive analysis case, given any taskset T and any finite-memory on- line scheduling algorithm A , we show that the competitive ratio of A in T can be computed in polynomial time in the size of the state space of A . Our approach is flexible as it also provides ways to model meaningful constraints on the released task sequences that determine the competitive ratio. We provide an experimental study of many well-known on-line scheduling algorithms, which demonstrates the feasibility of our competitive analysis approach that effectively replaces human ingenuity (required Preliminary versions of this paper have appeared in Chatterjee et al. ( 2013 , 2014 ). B Andreas Pavlogiannis pavlogiannis@ist.ac.at Krishnendu Chatterjee krish.chat@ist.ac.at Alexander Kößler koe@ecs.tuwien.ac.at Ulrich Schmid s@ecs.tuwien.ac.at 1 IST Austria (Institute of Science and Technology Austria), Am Campus 1, 3400 Klosterneuburg, Austria 2 Embedded Computing Systems Group, Vienna University of Technology, Treitlstrasse 3, 1040 Vienna, Austria 123 Real-Time Syst for finding worst-case scenarios) by computing power. For the competitive synthesis case, we are just given a taskset T , and the goal is to automatically synthesize an opti- mal on-line scheduling algorithm A , i.e., one that guarantees the largest competitive ratio possible for T . We show how the competitive synthesis problem can be reduced to a two-player graph game with partial information, and establish that the compu- tational complexity of solving this game is Np -complete. The competitive synthesis problem is hence in Np in the size of the state space of the non-deterministic labeled transition system encoding the taskset. Overall, the proposed framework assists in the selection of suitable scheduling algorithms for a given taskset, which is in fact the most common situation in real-time systems design. },
author = {Chatterjee, Krishnendu and Pavlogiannis, Andreas and Kößler, Alexander and Schmid, Ulrich},
journal = {Real-Time Systems},
number = {1},
pages = {166 -- 207},
publisher = {Springer},
title = {{Automated competitive analysis of real time scheduling with graph games}},
doi = {10.1007/s11241-017-9293-4},
volume = {54},
year = {2018},
}
@inbook{86,
abstract = {Responsiveness—the requirement that every request to a system be eventually handled—is one of the fundamental liveness properties of a reactive system. Average response time is a quantitative measure for the responsiveness requirement used commonly in performance evaluation. We show how average response time can be computed on state-transition graphs, on Markov chains, and on game graphs. In all three cases, we give polynomial-time algorithms.},
author = {Chatterjee, Krishnendu and Henzinger, Thomas A and Otop, Jan},
booktitle = {Principles of Modeling},
editor = {Lohstroh, Marten and Derler, Patricia and Sirjani, Marjan},
pages = {143 -- 161},
publisher = {Springer},
title = {{Computing average response time}},
doi = {10.1007/978-3-319-95246-8_9},
volume = {10760},
year = {2018},
}
@article{454,
abstract = {Direct reciprocity is a mechanism for cooperation among humans. Many of our daily interactions are repeated. We interact repeatedly with our family, friends, colleagues, members of the local and even global community. In the theory of repeated games, it is a tacit assumption that the various games that a person plays simultaneously have no effect on each other. Here we introduce a general framework that allows us to analyze “crosstalk” between a player’s concurrent games. In the presence of crosstalk, the action a person experiences in one game can alter the person’s decision in another. We find that crosstalk impedes the maintenance of cooperation and requires stronger levels of forgiveness. The magnitude of the effect depends on the population structure. In more densely connected social groups, crosstalk has a stronger effect. A harsh retaliator, such as Tit-for-Tat, is unable to counteract crosstalk. The crosstalk framework provides a unified interpretation of direct and upstream reciprocity in the context of repeated games.},
author = {Reiter, Johannes and Hilbe, Christian and Rand, David and Chatterjee, Krishnendu and Nowak, Martin},
journal = {Nature Communications},
number = {1},
publisher = {Nature Publishing Group},
title = {{Crosstalk in concurrent repeated games impedes direct reciprocity and requires stronger levels of forgiveness}},
doi = {10.1038/s41467-017-02721-8},
volume = {9},
year = {2018},
}
@article{157,
abstract = {Social dilemmas occur when incentives for individuals are misaligned with group interests 1-7 . According to the 'tragedy of the commons', these misalignments can lead to overexploitation and collapse of public resources. The resulting behaviours can be analysed with the tools of game theory 8 . The theory of direct reciprocity 9-15 suggests that repeated interactions can alleviate such dilemmas, but previous work has assumed that the public resource remains constant over time. Here we introduce the idea that the public resource is instead changeable and depends on the strategic choices of individuals. An intuitive scenario is that cooperation increases the public resource, whereas defection decreases it. Thus, cooperation allows the possibility of playing a more valuable game with higher payoffs, whereas defection leads to a less valuable game. We analyse this idea using the theory of stochastic games 16-19 and evolutionary game theory. We find that the dependence of the public resource on previous interactions can greatly enhance the propensity for cooperation. For these results, the interaction between reciprocity and payoff feedback is crucial: neither repeated interactions in a constant environment nor single interactions in a changing environment yield similar cooperation rates. Our framework shows which feedbacks between exploitation and environment - either naturally occurring or designed - help to overcome social dilemmas.},
author = {Hilbe, Christian and Šimsa, Štepán and Chatterjee, Krishnendu and Nowak, Martin},
journal = {Nature},
number = {7713},
pages = {246 -- 249},
publisher = {Nature Publishing Group},
title = {{Evolution of cooperation in stochastic games}},
doi = {10.1038/s41586-018-0277-x},
volume = {559},
year = {2018},
}
@inproceedings{25,
abstract = {Partially observable Markov decision processes (POMDPs) are the standard models for planning under uncertainty with both finite and infinite horizon. Besides the well-known discounted-sum objective, indefinite-horizon objective (aka Goal-POMDPs) is another classical objective for POMDPs. In this case, given a set of target states and a positive cost for each transition, the optimization objective is to minimize the expected total cost until a target state is reached. In the literature, RTDP-Bel or heuristic search value iteration (HSVI) have been used for solving Goal-POMDPs. Neither of these algorithms has theoretical convergence guarantees, and HSVI may even fail to terminate its trials. We give the following contributions: (1) We discuss the challenges introduced in Goal-POMDPs and illustrate how they prevent the original HSVI from converging. (2) We present a novel algorithm inspired by HSVI, termed Goal-HSVI, and show that our algorithm has convergence guarantees. (3) We show that Goal-HSVI outperforms RTDP-Bel on a set of well-known examples.},
author = {Horák, Karel and Bošanský, Branislav and Chatterjee, Krishnendu},
booktitle = {Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence},
location = {Stockholm, Sweden},
pages = {4764 -- 4770},
publisher = {IJCAI},
title = {{Goal-HSVI: Heuristic search value iteration for goal-POMDPs}},
doi = {10.24963/ijcai.2018/662 },
volume = {2018-July},
year = {2018},
}
@inproceedings{311,
abstract = {Smart contracts are computer programs that are executed by a network of mutually distrusting agents, without the need of an external trusted authority. Smart contracts handle and transfer assets of considerable value (in the form of crypto-currency like Bitcoin). Hence, it is crucial that their implementation is bug-free. We identify the utility (or expected payoff) of interacting with such smart contracts as the basic and canonical quantitative property for such contracts. We present a framework for such quantitative analysis of smart contracts. Such a formal framework poses new and novel research challenges in programming languages, as it requires modeling of game-theoretic aspects to analyze incentives for deviation from honest behavior and modeling utilities which are not specified as standard temporal properties such as safety and termination. While game-theoretic incentives have been analyzed in the security community, their analysis has been restricted to the very special case of stateless games. However, to analyze smart contracts, stateful analysis is required as it must account for the different program states of the protocol. Our main contributions are as follows: we present (i)~a simplified programming language for smart contracts; (ii)~an automatic translation of the programs to state-based games; (iii)~an abstraction-refinement approach to solve such games; and (iv)~experimental results on real-world-inspired smart contracts.},
author = {Chatterjee, Krishnendu and Goharshady, Amir and Velner, Yaron},
location = {Thessaloniki, Greece},
pages = {739 -- 767},
publisher = {Springer},
title = {{Quantitative analysis of smart contracts}},
doi = {10.1007/978-3-319-89884-1_26},
volume = {10801},
year = {2018},
}
@inproceedings{141,
abstract = {Given a model and a specification, the fundamental model-checking problem asks for algorithmic verification of whether the model satisfies the specification. We consider graphs and Markov decision processes (MDPs), which are fundamental models for reactive systems. One of the very basic specifications that arise in verification of reactive systems is the strong fairness (aka Streett) objective. Given different types of requests and corresponding grants, the objective requires that for each type, if the request event happens infinitely often, then the corresponding grant event must also happen infinitely often. All ω -regular objectives can be expressed as Streett objectives and hence they are canonical in verification. To handle the state-space explosion, symbolic algorithms are required that operate on a succinct implicit representation of the system rather than explicitly accessing the system. While explicit algorithms for graphs and MDPs with Streett objectives have been widely studied, there has been no improvement of the basic symbolic algorithms. The worst-case numbers of symbolic steps required for the basic symbolic algorithms are as follows: quadratic for graphs and cubic for MDPs. In this work we present the first sub-quadratic symbolic algorithm for graphs with Streett objectives, and our algorithm is sub-quadratic even for MDPs. Based on our algorithmic insights we present an implementation of the new symbolic approach and show that it improves the existing approach on several academic benchmark examples.},
author = {Chatterjee, Krishnendu and Henzinger, Monika and Loitzenbauer, Veronika and Oraee, Simin and Toman, Viktor},
location = {Oxford, United Kingdom},
pages = {178--197},
publisher = {Springer},
title = {{Symbolic algorithms for graphs and Markov decision processes with fairness objectives}},
doi = {10.1007/978-3-319-96142-2_13},
volume = {10982},
year = {2018},
}
@article{2,
abstract = {Indirect reciprocity explores how humans act when their reputation is at stake, and which social norms they use to assess the actions of others. A crucial question in indirect reciprocity is which social norms can maintain stable cooperation in a society. Past research has highlighted eight such norms, called “leading-eight” strategies. This past research, however, is based on the assumption that all relevant information about other population members is publicly available and that everyone agrees on who is good or bad. Instead, here we explore the reputation dynamics when information is private and noisy. We show that under these conditions, most leading-eight strategies fail to evolve. Those leading-eight strategies that do evolve are unable to sustain full cooperation.Indirect reciprocity is a mechanism for cooperation based on shared moral systems and individual reputations. It assumes that members of a community routinely observe and assess each other and that they use this information to decide who is good or bad, and who deserves cooperation. When information is transmitted publicly, such that all community members agree on each other’s reputation, previous research has highlighted eight crucial moral systems. These “leading-eight” strategies can maintain cooperation and resist invasion by defectors. However, in real populations individuals often hold their own private views of others. Once two individuals disagree about their opinion of some third party, they may also see its subsequent actions in a different light. Their opinions may further diverge over time. Herein, we explore indirect reciprocity when information transmission is private and noisy. We find that in the presence of perception errors, most leading-eight strategies cease to be stable. Even if a leading-eight strategy evolves, cooperation rates may drop considerably when errors are common. Our research highlights the role of reliable information and synchronized reputations to maintain stable moral systems.},
author = {Hilbe, Christian and Schmid, Laura and Tkadlec, Josef and Chatterjee, Krishnendu and Nowak, Martin},
journal = {PNAS},
number = {48},
pages = {12241--12246},
publisher = {National Academy of Sciences},
title = {{Indirect reciprocity with private noisy and incomplete information}},
doi = {10.1073/pnas.1810565115 },
volume = {115},
year = {2018},
}
@inproceedings{297,
abstract = {Graph games played by two players over finite-state graphs are central in many problems in computer science. In particular, graph games with ω -regular winning conditions, specified as parity objectives, which can express properties such as safety, liveness, fairness, are the basic framework for verification and synthesis of reactive systems. The decisions for a player at various states of the graph game are represented as strategies. While the algorithmic problem for solving graph games with parity objectives has been widely studied, the most prominent data-structure for strategy representation in graph games has been binary decision diagrams (BDDs). However, due to the bit-level representation, BDDs do not retain the inherent flavor of the decisions of strategies, and are notoriously hard to minimize to obtain succinct representation. In this work we propose decision trees for strategy representation in graph games. Decision trees retain the flavor of decisions of strategies and allow entropy-based minimization to obtain succinct trees. However, decision trees work in settings (e.g., probabilistic models) where errors are allowed, and overfitting of data is typically avoided. In contrast, for strategies in graph games no error is allowed, and the decision tree must represent the entire strategy. We develop new techniques to extend decision trees to overcome the above obstacles, while retaining the entropy-based techniques to obtain succinct trees. We have implemented our techniques to extend the existing decision tree solvers. We present experimental results for problems in reactive synthesis to show that decision trees provide a much more efficient data-structure for strategy representation as compared to BDDs.},
author = {Brázdil, Tomáš and Chatterjee, Krishnendu and Kretinsky, Jan and Toman, Viktor},
location = {Thessaloniki, Greece},
pages = {385 -- 407},
publisher = {Springer},
title = {{Strategy representation by decision trees in reactive synthesis}},
doi = {10.1007/978-3-319-89960-2_21},
volume = {10805},
year = {2018},
}
@article{293,
abstract = {People sometimes make their admirable deeds and accomplishments hard to spot, such as by giving anonymously or avoiding bragging. Such ‘buried’ signals are hard to reconcile with standard models of signalling or indirect reciprocity, which motivate costly pro-social behaviour by reputational gains. To explain these phenomena, we design a simple game theory model, which we call the signal-burying game. This game has the feature that senders can bury their signal by deliberately reducing the probability of the signal being observed. If the signal is observed, however, it is identified as having been buried. We show under which conditions buried signals can be maintained, using static equilibrium concepts and calculations of the evolutionary dynamics. We apply our analysis to shed light on a number of otherwise puzzling social phenomena, including modesty, anonymous donations, subtlety in art and fashion, and overeagerness.},
author = {Hoffman, Moshe and Hilbe, Christian and Nowak, Martin},
journal = {Nature Human Behaviour},
pages = {397 -- 404},
publisher = {Nature Publishing Group},
title = {{The signal-burying game can explain why we obscure positive traits and good deeds}},
doi = {10.1038/s41562-018-0354-z},
volume = {2},
year = {2018},
}
@inproceedings{325,
abstract = {Probabilistic programs extend classical imperative programs with real-valued random variables and random branching. The most basic liveness property for such programs is the termination property. The qualitative (aka almost-sure) termination problem asks whether a given program program terminates with probability 1. While ranking functions provide a sound and complete method for non-probabilistic programs, the extension of them to probabilistic programs is achieved via ranking supermartingales (RSMs). Although deep theoretical results have been established about RSMs, their application to probabilistic programs with nondeterminism has been limited only to programs of restricted control-flow structure. For non-probabilistic programs, lexicographic ranking functions provide a compositional and practical approach for termination analysis of real-world programs. In this work we introduce lexicographic RSMs and show that they present a sound method for almost-sure termination of probabilistic programs with nondeterminism. We show that lexicographic RSMs provide a tool for compositional reasoning about almost-sure termination, and for probabilistic programs with linear arithmetic they can be synthesized efficiently (in polynomial time). We also show that with additional restrictions even asymptotic bounds on expected termination time can be obtained through lexicographic RSMs. Finally, we present experimental results on benchmarks adapted from previous work to demonstrate the effectiveness of our approach.},
author = {Agrawal, Sheshansh and Chatterjee, Krishnendu and Novotny, Petr},
location = {Los Angeles, CA, USA},
number = {POPL},
publisher = {ACM},
title = {{Lexicographic ranking supermartingales: an efficient approach to termination of probabilistic programs}},
doi = {10.1145/3158122},
volume = {2},
year = {2018},
}
@inproceedings{34,
abstract = {Partially observable Markov decision processes (POMDPs) are widely used in probabilistic planning problems in which an agent interacts with an environment using noisy and imprecise sensors. We study a setting in which the sensors are only partially defined and the goal is to synthesize “weakest” additional sensors, such that in the resulting POMDP, there is a small-memory policy for the agent that almost-surely (with probability 1) satisfies a reachability objective. We show that the problem is NP-complete, and present a symbolic algorithm by encoding the problem into SAT instances. We illustrate trade-offs between the amount of memory of the policy and the number of additional sensors on a simple example. We have implemented our approach and consider three classical POMDP examples from the literature, and show that in all the examples the number of sensors can be significantly decreased (as compared to the existing solutions in the literature) without increasing the complexity of the policies.},
author = {Chatterjee, Krishnendu and Chemlík, Martin and Topcu, Ufuk},
location = {Delft, Netherlands},
pages = {47 -- 55},
publisher = {AAAI Press},
title = {{Sensor synthesis for POMDPs with reachability objectives}},
volume = {2018},
year = {2018},
}
@article{419,
abstract = {Reciprocity is a major factor in human social life and accounts for a large part of cooperation in our communities. Direct reciprocity arises when repeated interactions occur between the same individuals. The framework of iterated games formalizes this phenomenon. Despite being introduced more than five decades ago, the concept keeps offering beautiful surprises. Recent theoretical research driven by new mathematical tools has proposed a remarkable dichotomy among the crucial strategies: successful individuals either act as partners or as rivals. Rivals strive for unilateral advantages by applying selfish or extortionate strategies. Partners aim to share the payoff for mutual cooperation, but are ready to fight back when being exploited. Which of these behaviours evolves depends on the environment. Whereas small population sizes and a limited number of rounds favour rivalry, partner strategies are selected when populations are large and relationships stable. Only partners allow for evolution of cooperation, while the rivals’ attempt to put themselves first leads to defection. Hilbe et al. synthesize recent theoretical work on zero-determinant and ‘rival’ versus ‘partner’ strategies in social dilemmas. They describe the environments under which these contrasting selfish or cooperative strategies emerge in evolution.},
author = {Hilbe, Christian and Chatterjee, Krishnendu and Nowak, Martin},
journal = {Nature Human Behaviour},
pages = {469–477},
publisher = {Nature Publishing Group},
title = {{Partners and rivals in direct reciprocity}},
doi = {10.1038/s41562-018-0320-9},
volume = {2},
year = {2018},
}
@inproceedings{5679,
abstract = {We study the almost-sure termination problem for probabilistic programs. First, we show that supermartingales with lower bounds on conditional absolute difference provide a sound approach for the almost-sure termination problem. Moreover, using this approach we can obtain explicit optimal bounds on tail probabilities of non-termination within a given number of steps. Second, we present a new approach based on Central Limit Theorem for the almost-sure termination problem, and show that this approach can establish almost-sure termination of programs which none of the existing approaches can handle. Finally, we discuss algorithmic approaches for the two above methods that lead to automated analysis techniques for almost-sure termination of probabilistic programs.},
author = {Huang, Mingzhang and Fu, Hongfei and Chatterjee, Krishnendu},
editor = {Ryu, Sukyoung},
isbn = {9783030027674},
issn = {03029743},
location = {Wellington, New Zealand},
pages = {181--201},
publisher = {Springer},
title = {{New approaches for almost-sure termination of probabilistic programs}},
doi = {10.1007/978-3-030-02768-1_11},
volume = {11275},
year = {2018},
}
@unpublished{5977,
abstract = {We consider the stochastic shortest path (SSP)problem for succinct Markov decision processes(MDPs), where the MDP consists of a set of vari-ables, and a set of nondeterministic rules that up-date the variables. First, we show that several ex-amples from the AI literature can be modeled assuccinct MDPs. Then we present computationalapproaches for upper and lower bounds for theSSP problem: (a) for computing upper bounds, ourmethod is polynomial-time in the implicit descrip-tion of the MDP; (b) for lower bounds, we present apolynomial-time (in the size of the implicit descrip-tion) reduction to quadratic programming. Our ap-proach is applicable even to infinite-state MDPs.Finally, we present experimental results to demon-strate the effectiveness of our approach on severalclassical examples from the AI literature.},
author = {Chatterjee, Krishnendu and Fu, Hongfei and Goharshady, Amir and Okati, Nastaran},
booktitle = {ArXiv},
publisher = {ArXiv},
title = {{Computational Approaches for Stochastic Shortest Path on Succinct MDPs}},
year = {2018},
}
@article{5751,
abstract = {Because of the intrinsic randomness of the evolutionary process, a mutant with a fitness advantage has some chance to be selected but no certainty. Any experiment that searches for advantageous mutants will lose many of them due to random drift. It is therefore of great interest to find population structures that improve the odds of advantageous mutants. Such structures are called amplifiers of natural selection: they increase the probability that advantageous mutants are selected. Arbitrarily strong amplifiers guarantee the selection of advantageous mutants, even for very small fitness advantage. Despite intensive research over the past decade, arbitrarily strong amplifiers have remained rare. Here we show how to construct a large variety of them. Our amplifiers are so simple that they could be useful in biotechnology, when optimizing biological molecules, or as a diagnostic tool, when searching for faster dividing cells or viruses. They could also occur in natural population structures.},
author = {Pavlogiannis, Andreas and Tkadlec, Josef and Chatterjee, Krishnendu and Nowak, Martin A.},
issn = {2399-3642},
journal = {Communications Biology},
number = {1},
publisher = {Springer Nature},
title = {{Construction of arbitrarily strong amplifiers of natural selection using evolutionary graph theory}},
doi = {10.1038/s42003-018-0078-7},
volume = {1},
year = {2018},
}
@article{1065,
abstract = {We consider the problem of reachability in pushdown graphs. We study the problem for pushdown graphs with constant treewidth. Even for pushdown graphs with treewidth 1, for the reachability problem we establish the following: (i) the problem is PTIME-complete, and (ii) any subcubic algorithm for the problem would contradict the k-clique conjecture and imply faster combinatorial algorithms for cliques in graphs.},
author = {Chatterjee, Krishnendu and Osang, Georg F},
issn = {00200190},
journal = {Information Processing Letters},
pages = {25 -- 29},
publisher = {Elsevier},
title = {{Pushdown reachability with constant treewidth}},
doi = {10.1016/j.ipl.2017.02.003},
volume = {122},
year = {2017},
}
@article{1407,
abstract = {We consider the problem of computing the set of initial states of a dynamical system such that there exists a control strategy to ensure that the trajectories satisfy a temporal logic specification with probability 1 (almost-surely). We focus on discrete-time, stochastic linear dynamics and specifications given as formulas of the Generalized Reactivity(1) fragment of Linear Temporal Logic over linear predicates in the states of the system. We propose a solution based on iterative abstraction-refinement, and turn-based 2-player probabilistic games. While the theoretical guarantee of our algorithm after any finite number of iterations is only a partial solution, we show that if our algorithm terminates, then the result is the set of all satisfying initial states. Moreover, for any (partial) solution our algorithm synthesizes witness control strategies to ensure almost-sure satisfaction of the temporal logic specification. While the proposed algorithm guarantees progress and soundness in every iteration, it is computationally demanding. We offer an alternative, more efficient solution for the reachability properties that decomposes the problem into a series of smaller problems of the same type. All algorithms are demonstrated on an illustrative case study.},
author = {Svoreňová, Mária and Kretinsky, Jan and Chmelik, Martin and Chatterjee, Krishnendu and Cěrná, Ivana and Belta, Cǎlin},
journal = {Nonlinear Analysis: Hybrid Systems},
number = {2},
pages = {230 -- 253},
publisher = {Elsevier},
title = {{Temporal logic control for stochastic linear systems using abstraction refinement of probabilistic games}},
doi = {10.1016/j.nahs.2016.04.006},
volume = {23},
year = {2017},
}
@article{681,
abstract = {Two-player games on graphs provide the theoretical framework for many important problems such as reactive synthesis. While the traditional study of two-player zero-sum games has been extended to multi-player games with several notions of equilibria, they are decidable only for perfect-information games, whereas several applications require imperfect-information. In this paper we propose a new notion of equilibria, called doomsday equilibria, which is a strategy profile where all players satisfy their own objective, and if any coalition of players deviates and violates even one of the players' objective, then the objective of every player is violated. We present algorithms and complexity results for deciding the existence of doomsday equilibria for various classes of ω-regular objectives, both for imperfect-information games, and for perfect-information games. We provide optimal complexity bounds for imperfect-information games, and in most cases for perfect-information games.},
author = {Chatterjee, Krishnendu and Doyen, Laurent and Filiot, Emmanuel and Raskin, Jean},
issn = {08905401},
journal = {Information and Computation},
pages = {296 -- 315},
publisher = {Elsevier},
title = {{Doomsday equilibria for omega-regular games}},
doi = {10.1016/j.ic.2016.10.012},
volume = {254},
year = {2017},
}