Policy Testing in Markov Decision Processes

• URL: http://arxiv.org/abs/2505.15342v1
• Date: Wed, 21 May 2025 10:13:54 GMT
• Title: Policy Testing in Markov Decision Processes
• Authors: Kaito Ariu, Po-An Wang, Alexandre Proutiere, Kenshi Abe,
• Abstract summary: We study the policy testing problem in discounted decision processes (MDP) under the fixed-confidence setting.<n>The goal is to determine whether the value of a given policy exceeds a numerical threshold.
• Score: 48.642181362172906
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the policy testing problem in discounted Markov decision processes (MDPs) under the fixed-confidence setting. The goal is to determine whether the value of a given policy exceeds a specified threshold while minimizing the number of observations. We begin by deriving an instance-specific lower bound that any algorithm must satisfy. This lower bound is characterized as the solution to an optimization problem with non-convex constraints. We propose a policy testing algorithm inspired by this optimization problem--a common approach in pure exploration problems such as best-arm identification, where asymptotically optimal algorithms often stem from such optimization-based characterizations. As for other pure exploration tasks in MDPs, however, the non-convex constraints in the lower-bound problem present significant challenges, raising doubts about whether statistically optimal and computationally tractable algorithms can be designed. To address this, we reformulate the lower-bound problem by interchanging the roles of the objective and the constraints, yielding an alternative problem with a non-convex objective but convex constraints. Strikingly, this reformulated problem admits an interpretation as a policy optimization task in a newly constructed reversed MDP. Leveraging recent advances in policy gradient methods, we efficiently solve this problem and use it to design a policy testing algorithm that is statistically optimal--matching the instance-specific lower bound on sample complexity--while remaining computationally tractable. We validate our approach with numerical experiments.

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)
• Policy Gradient Algorithms for Robust MDPs with Non-Rectangular Uncertainty Sets [10.26382228865201]
  We propose policy gradient algorithms for robust infinite-horizon Markov decision processes (MDPs) with non-rectangular uncertainty sets. The corresponding robust MDPs cannot be solved with dynamic programming techniques and are in fact provably intractable. We thus present the first complete solution scheme for robust MDPs with non-rectangular uncertainty sets offering global optimality guarantees.
  arXiv  Detail & Related papers  (2023-05-30T13:02:25Z)
• High-probability sample complexities for policy evaluation with linear function approximation [88.87036653258977]
  We investigate the sample complexities required to guarantee a predefined estimation error of the best linear coefficients for two widely-used policy evaluation algorithms. We establish the first sample complexity bound with high-probability convergence guarantee that attains the optimal dependence on the tolerance level.
  arXiv  Detail & Related papers  (2023-05-30T12:58:39Z)
• Multi-Objective Policy Gradients with Topological Constraints [108.10241442630289]
  We present a new algorithm for a policy gradient in TMDPs by a simple extension of the proximal policy optimization (PPO) algorithm. We demonstrate this on a real-world multiple-objective navigation problem with an arbitrary ordering of objectives both in simulation and on a real robot.
  arXiv  Detail & Related papers  (2022-09-15T07:22:58Z)
• Instance-Dependent Confidence and Early Stopping for Reinforcement Learning [99.57168572237421]
  Various algorithms for reinforcement learning (RL) exhibit dramatic variation in their convergence rates as a function of problem structure. This research provides guarantees that explain textitex post the performance differences observed. A natural next step is to convert these theoretical guarantees into guidelines that are useful in practice.
  arXiv  Detail & Related papers  (2022-01-21T04:25:35Z)
• 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)
• Variance-Reduced Off-Policy Memory-Efficient Policy Search [61.23789485979057]
  Off-policy policy optimization is a challenging problem in reinforcement learning. Off-policy algorithms are memory-efficient and capable of learning from off-policy samples.
  arXiv  Detail & Related papers  (2020-09-14T16:22:46Z)

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.