Learning Algorithms for Verification of Markov Decision Processes

• URL: http://arxiv.org/abs/2403.09184v3
• Date: Tue, 05 Nov 2024 09:51:16 GMT
• Title: Learning Algorithms for Verification of Markov Decision Processes
• Authors: Tomáš Brázdil, Krishnendu Chatterjee, Martin Chmelik, Vojtěch Forejt, Jan Křetínský, Marta Kwiatkowska, Tobias Meggendorfer, David Parker, Mateusz Ujma,
• Abstract summary: We present a general framework for applying learning algorithms to the verification of Markov decision processes (MDPs) The presented framework focuses on probabilistic reachability, which is a core problem in verification.
• Score: 20.5951492453299
• License:
• Abstract: We present a general framework for applying learning algorithms and heuristical guidance to the verification of Markov decision processes (MDPs). The primary goal of our techniques is to improve performance by avoiding an exhaustive exploration of the state space, instead focussing on particularly relevant areas of the system, guided by heuristics. Our work builds on the previous results of Br{\'{a}}zdil et al., significantly extending it as well as refining several details and fixing errors. The presented framework focuses on probabilistic reachability, which is a core problem in verification, and is instantiated in two distinct scenarios. The first assumes that full knowledge of the MDP is available, in particular precise transition probabilities. It performs a heuristic-driven partial exploration of the model, yielding precise lower and upper bounds on the required probability. The second tackles the case where we may only sample the MDP without knowing the exact transition dynamics. Here, we obtain probabilistic guarantees, again in terms of both the lower and upper bounds, which provides efficient stopping criteria for the approximation. In particular, the latter is an extension of statistical model-checking (SMC) for unbounded properties in MDPs. In contrast to other related approaches, we do not restrict our attention to time-bounded (finite-horizon) or discounted properties, nor assume any particular structural properties of the MDP.

Related papers

• Sound Heuristic Search Value Iteration for Undiscounted POMDPs with Reachability Objectives [16.101435842520473]
  This paper studies the challenging yet important problem in POMDPs known as the (indefinite-horizon) Maximal Reachability Probability Problem. Inspired by the success of point-based methods developed for discounted problems, we study their extensions to MRPP. We present a novel algorithm that leverages the strengths of these techniques for efficient exploration of the belief space.
  arXiv  Detail & Related papers  (2024-06-05T02:33:50Z)
• What Are the Odds? Improving the foundations of Statistical Model Checking [3.789219860006095]
  Markov decision processes (MDPs) are a fundamental model for decision making under uncertainty. Traditionally verification algorithms assume exact knowledge of the probabilities that govern the behaviour of an MDP. We propose specialised approaches that exploit our knowledge of the MDP.
  arXiv  Detail & Related papers  (2024-04-08T11:47:46Z)
• Efficient Model-Free Exploration in Low-Rank MDPs [76.87340323826945]
  Low-Rank Markov Decision Processes offer a simple, yet expressive framework for RL with function approximation. Existing algorithms are either (1) computationally intractable, or (2) reliant upon restrictive statistical assumptions. We propose the first provably sample-efficient algorithm for exploration in Low-Rank MDPs.
  arXiv  Detail & Related papers  (2023-07-08T15:41:48Z)
• Provably Efficient UCB-type Algorithms For Learning Predictive State Representations [55.00359893021461]
  The sequential decision-making problem is statistically learnable if it admits a low-rank structure modeled by predictive state representations (PSRs) This paper proposes the first known UCB-type approach for PSRs, featuring a novel bonus term that upper bounds the total variation distance between the estimated and true models. In contrast to existing approaches for PSRs, our UCB-type algorithms enjoy computational tractability, last-iterate guaranteed near-optimal policy, and guaranteed model accuracy.
  arXiv  Detail & Related papers  (2023-07-01T18:35:21Z)
• PAC Statistical Model Checking of Mean Payoff in Discrete- and Continuous-Time MDP [0.34410212782758043]
  We provide the first algorithm to compute mean payoff probably approximately correctly in unknown MDP. We do not require any knowledge of the state space, only a lower bound on the minimum transition probability. In addition to providing probably approximately correct (PAC) bounds for our algorithm, we also demonstrate its practical nature by running experiments on standard benchmarks.
  arXiv  Detail & Related papers  (2022-06-03T09:13:27Z)
• Reinforcement Learning with a Terminator [80.34572413850186]
  We learn the parameters of the TerMDP and leverage the structure of the estimation problem to provide state-wise confidence bounds. We use these to construct a provably-efficient algorithm, which accounts for termination, and bound its regret.
  arXiv  Detail & Related papers  (2022-05-30T18:40:28Z)
• Regret Analysis in Deterministic Reinforcement Learning [78.31410227443102]
  We study the problem of regret, which is central to the analysis and design of optimal learning algorithms. We present logarithmic problem-specific regret lower bounds that explicitly depend on the system parameter.
  arXiv  Detail & Related papers  (2021-06-27T23:41:57Z)
• Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection [7.685002911021767]
  We introduce an algorithm that efficiently learns policies in non-stationary environments. It analyzes a possibly infinite stream of data and computes, in real-time, high-confidence change-point detection statistics. We show that (i) this algorithm minimizes the delay until unforeseen changes to a context are detected, thereby allowing for rapid responses.
  arXiv  Detail & Related papers  (2021-05-20T01:57:52Z)
• Incremental Verification of Fixed-Point Implementations of Neural Networks [0.19573380763700707]
  We develop and evaluate a novel symbolic verification framework using incremental bounded model checking (BMC), satisfiability modulo theories (SMT), and invariant inference. Our approach was able to verify and produce examples for 85.8% of 21 test cases considering different input images, and 100% of the properties related to covering methods.
  arXiv  Detail & Related papers  (2020-12-21T10:03:44Z)
• Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation [99.92568326314667]
  We propose the amortized conditional normalized maximum likelihood (ACNML) method as a scalable general-purpose approach for uncertainty estimation. Our algorithm builds on the conditional normalized maximum likelihood (CNML) coding scheme, which has minimax optimal properties according to the minimum description length principle. We demonstrate that ACNML compares favorably to a number of prior techniques for uncertainty estimation in terms of calibration on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2020-11-05T08:04:34Z)
• Adaptive Sampling for Best Policy Identification in Markov Decision Processes [79.4957965474334]
  We investigate the problem of best-policy identification in discounted Markov Decision (MDPs) when the learner has access to a generative model. The advantages of state-of-the-art algorithms are discussed and illustrated.
  arXiv  Detail & Related papers  (2020-09-28T15:22:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.