Searcharxiv⌕ Search

arXiv subjects

Tobias Meggendorfer

Publications and source records attributed to Tobias Meggendorfer.

31 records · Page 2Linked to original sources
arXiv2023

Guessing Winning Policies in LTL Synthesis by Semantic Learning

We provide a learning-based technique for guessing a winning strategy in a parity game originating from an LTL synthesis problem. A cheaply obtained guess can be useful in several applications. Not only can the guessed strategy be applied as best-effort in cases where the game's huge size prohibits rigorous approaches, but it can also increase the scalability of rigorous LTL synthesis in several ways. Firstly, checking whether a guessed strategy is winning is easier than constructing one. Secondly, even if the guess is wrong in some places, it can be fixed by strategy iteration faster than constructing one from scratch. Thirdly, the guess can be used in on-the-fly approaches to prioritize exploration in the most fruitful directions. In contrast to previous works, we (i)~reflect the highly structured logical information in game's states, the so-called semantic labelling, coming from the recent LTL-to-automata translations, and (ii)~learn to reflect it properly by learning from previously solved games, bringing the solving process closer to human-like reasoning.

cs.AI↗
arXiv2023

Stopping Criteria for Value Iteration on Stochastic Games with Quantitative Objectives

A classic solution technique for Markov decision processes (MDP) and stochastic games (SG) is value iteration (VI). Due to its good practical performance, this approximative approach is typically preferred over exact techniques, even though no practical bounds on the imprecision of the result could be given until recently. As a consequence, even the most used model checkers could return arbitrarily wrong results. Over the past decade, different works derived stopping criteria, indicating when the precision reaches the desired level, for various settings, in particular MDP with reachability, total reward, and mean payoff, and SG with reachability. In this paper, we provide the first stopping criteria for VI on SG with total reward and mean payoff, yielding the first anytime algorithms in these settings. To this end, we provide the solution in two flavours: First through a reduction to the MDP case and second directly on SG. The former is simpler and automatically utilizes any advances on MDP. The latter allows for more local computations, heading towards better practical efficiency. Our solution unifies the previously mentioned approaches for MDP and SG and their underlying ideas. To achieve this, we isolate objective-specific subroutines as well as identify objective-independent concepts. These structural concepts, while surprisingly simple, form the very essence of the unified solution.

cs.AI↗
arXiv2023

Correct Approximation of Stationary Distributions

A classical problem for Markov chains is determining their stationary (or steady-state) distribution. This problem has an equally classical solution based on eigenvectors and linear equation systems. However, this approach does not scale to large instances, and iterative solutions are desirable. It turns out that a naive approach, as used by current model checkers, may yield completely wrong results. We present a new approach, which utilizes recent advances in partial exploration and mean payoff computation to obtain a correct, converging approximation.

eess.SY↗
arXiv2022

Satisfiability Bounds for $ω$-Regular Properties in Bounded-Parameter Markov Decision Processes

We consider the problem of computing minimum and maximum probabilities of satisfying an $ω$-regular property in a bounded-parameter Markov decision process (BMDP). BMDP arise from Markov decision processes (MDP) by allowing for uncertainty on the transition probabilities in the form of intervals where the actual probabilities are unknown. $ω$-regular languages form a large class of properties, expressible as, e.g., Rabin or parity automata, encompassing rich specifications such as linear temporal logic. In a BMDP the probability to satisfy the property depends on the unknown transitions probabilities as well as on the policy. In this paper, we compute the extreme values. This solves the problem specifically suggested by Dutreix and Coogan in CDC 2018, extending their results on interval Markov chains with no adversary. The main idea is to reinterpret their work as analysis of interval MDP and accordingly the BMDP problem as analysis of an $ω$-regular stochastic game, where a solution is provided. This method extends smoothly further to bounded-parameter stochastic games.

cs.LO↗
arXiv2022

Anytime Guarantees for Reachability in Uncountable Markov Decision Processes

We consider the problem of approximating the reachability probabilities in Markov decision processes (MDP) with uncountable (continuous) state and action spaces. While there are algorithms that, for special classes of such MDP, provide a sequence of approximations converging to the true value in the limit, our aim is to obtain an algorithm with guarantees on the precision of the approximation. As this problem is undecidable in general, assumptions on the MDP are necessary. Our main contribution is to identify sufficient assumptions that are as weak as possible, thus approaching the "boundary" of which systems can be correctly and reliably analyzed. To this end, we also argue why each of our assumptions is necessary for algorithms based on processing finitely many observations. We present two solution variants. The first one provides converging lower bounds under weaker assumptions than typical ones from previous works concerned with guarantees. The second one then utilizes stronger assumptions to additionally provide converging upper bounds. Altogether, we obtain an anytime algorithm, i.e. yielding a sequence of approximants with known and iteratively improving precision, converging to the true value in the limit. Besides, due to the generality of our assumptions, our algorithms are very general templates, readily allowing for various heuristics from literature in contrast to, e.g., a specific discretization algorithm. Our theoretical contribution thus paves the way for future practical improvements without sacrificing correctness guarantees.

eess.SY↗
arXiv2022

Risk-aware Stochastic Shortest Path

We treat the problem of risk-aware control for stochastic shortest path (SSP) on Markov decision processes (MDP). Typically, expectation is considered for SSP, which however is oblivious to the incurred risk. We present an alternative view, instead optimizing conditional value-at-risk (CVaR), an established risk measure. We treat both Markov chains as well as MDP and introduce, through novel insights, two algorithms, based on linear programming and value iteration, respectively. Both algorithms offer precise and provably correct solutions. Evaluation of our prototype implementation shows that risk-aware control is feasible on several moderately sized models.

eess.SY↗
arXiv2020

Of Cores: A Partial-Exploration Framework for Markov Decision Processes

We introduce a framework for approximate analysis of Markov decision processes (MDP) with bounded-, unbounded-, and infinite-horizon properties. The main idea is to identify a "core" of an MDP, i.e., a subsystem where we provably remain with high probability, and to avoid computation on the less relevant rest of the state space. Although we identify the core using simulations and statistical techniques, it allows for rigorous error bounds in the analysis. Consequently, we obtain efficient analysis algorithms based on partial exploration for various settings, including the challenging case of strongly connected systems.

eess.SY↗
arXiv2019

Semantic Labelling and Learning for Parity Game Solving in LTL Synthesis

We propose "semantic labelling" as a novel ingredient for solving games in the context of LTL synthesis. It exploits recent advances in the automata-based approach, yielding more information for each state of the generated parity game than the game graph can capture. We utilize this extra information to improve standard approaches as follows. (i) Compared to strategy improvement (SI) with random initial strategy, a more informed initialization often yields a winning strategy directly without any computation. (ii) This initialization makes SI also yield smaller solutions. (iii) While Q-learning on the game graph turns out not too efficient, Q-learning with the semantic information becomes competitive to SI. Since already the simplest heuristics achieve significant improvements the experimental results demonstrate the utility of semantic labelling. This extra information opens the door to more advanced learning approaches both for initialization and improvement of strategies.

cs.LO↗
arXiv2018

Conditional Value-at-Risk for Reachability and Mean Payoff in Markov Decision Processes

We present the conditional value-at-risk (CVaR) in the context of Markov chains and Markov decision processes with reachability and mean-payoff objectives. CVaR quantifies risk by means of the expectation of the worst p-quantile. As such it can be used to design risk-averse systems. We consider not only CVaR constraints, but also introduce their conjunction with expectation constraints and quantile constraints (value-at-risk, VaR). We derive lower and upper bounds on the computational complexity of the respective decision problems and characterize the structure of the strategies in terms of memory and randomization.

cs.LO↗
arXiv2017

Efficient Strategy Iteration for Mean Payoff in Markov Decision Processes

Markov decision processes (MDPs) are standard models for probabilistic systems with non-deterministic behaviours. Mean payoff (or long-run average reward) provides a mathematically elegant formalism to express performance related properties. Strategy iteration is one of the solution techniques applicable in this context. While in many other contexts it is the technique of choice due to advantages over e.g. value iteration, such as precision or possibility of domain-knowledge-aware initialization, it is rarely used for MDPs, since there it scales worse than value iteration. We provide several techniques that speed up strategy iteration by orders of magnitude for many MDPs, eliminating the performance disadvantage while preserving all its advantages.

cs.PF↗
arXiv2017

Value Iteration for Long-run Average Reward in Markov Decision Processes

Markov decision processes (MDPs) are standard models for probabilistic systems with non-deterministic behaviours. Long-run average rewards provide a mathematically elegant formalism for expressing long term performance. Value iteration (VI) is one of the simplest and most efficient algorithmic approaches to MDPs with other properties, such as reachability objectives. Unfortunately, a naive extension of VI does not work for MDPs with long-run average rewards, as there is no known stopping criterion. In this work our contributions are threefold. (1) We refute a conjecture related to stopping criteria for MDPs with long-run average rewards. (2) We present two practical algorithms for MDPs with long-run average rewards based on VI. First, we show that a combination of applying VI locally for each maximal end-component (MEC) and VI for reachability objectives can provide approximation guarantees. Second, extending the above approach with a simulation-guided on-demand variant of VI, we present an anytime algorithm that is able to deal with very large models. (3) Finally, we present experimental results showing that our methods significantly outperform the standard approaches on several benchmarks.

eess.SY↗
arXiv2017

Index appearance record for transforming Rabin automata into parity automata

Transforming deterministic $ω$-automata into deterministic parity automata is traditionally done using variants of appearance records. We present a more efficient variant of this approach, tailored to Rabin automata, and several optimizations applicable to all appearance records. We compare the methods experimentally and find out that our method produces smaller automata than previous approaches. Moreover, the experiments demonstrate the potential of our method for LTL synthesis, using LTL-to-Rabin translators. It leads to significantly smaller parity automata when compared to state-of-the-art approaches on complex formulae.

cs.LO↗