Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces

• URL: http://arxiv.org/abs/2405.15509v1
• Date: Fri, 24 May 2024 12:53:07 GMT
• Title: Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces
• Authors: Angeliki Kamoutsi, Peter Schmitt-Förster, Tobias Sutter, Volkan Cevher, John Lygeros,
• Abstract summary: This work studies discrete-time discounted Markov decision processes with continuous state and action spaces. We first consider the case in which we have access to the entire expert policy and characterize the set of solutions to the inverse problem.
• Score: 47.907236421762626
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This work studies discrete-time discounted Markov decision processes with continuous state and action spaces and addresses the inverse problem of inferring a cost function from observed optimal behavior. We first consider the case in which we have access to the entire expert policy and characterize the set of solutions to the inverse problem by using occupation measures, linear duality, and complementary slackness conditions. To avoid trivial solutions and ill-posedness, we introduce a natural linear normalization constraint. This results in an infinite-dimensional linear feasibility problem, prompting a thorough analysis of its properties. Next, we use linear function approximators and adopt a randomized approach, namely the scenario approach and related probabilistic feasibility guarantees, to derive epsilon-optimal solutions for the inverse problem. We further discuss the sample complexity for a desired approximation accuracy. Finally, we deal with the more realistic case where we only have access to a finite set of expert demonstrations and a generative model and provide bounds on the error made when working with samples.

Related papers

• Trust-Region Sequential Quadratic Programming for Stochastic Optimization with Random Models [57.52124921268249]
  We propose a Trust Sequential Quadratic Programming method to find both first and second-order stationary points. To converge to first-order stationary points, our method computes a gradient step in each iteration defined by minimizing a approximation of the objective subject. To converge to second-order stationary points, our method additionally computes an eigen step to explore the negative curvature the reduced Hessian matrix.
  arXiv  Detail & Related papers  (2024-09-24T04:39:47Z)
• Online Non-convex Optimization with Long-term Non-convex Constraints [2.033434950296318]
  A novel Follow-the-Perturbed-Leader type algorithm is proposed and analyzed for solving general long-term constrained optimization problems in online manner. The proposed algorithm is applied to tackle a long-term (extreme value) constrained river pollutant source identification problem.
  arXiv  Detail & Related papers  (2023-11-04T15:08:36Z)
• A Sequential Quadratic Programming Method with High Probability Complexity Bounds for Nonlinear Equality Constrained Stochastic Optimization [2.3814052021083354]
  It is assumed that constraint function values and derivatives are available, but only programming approximations of the objective function and its associated derivatives can be computed. A high-probability bound on the iteration complexity of the algorithm to approximate first-order stationarity is derived.
  arXiv  Detail & Related papers  (2023-01-01T21:46:50Z)
• Fully Stochastic Trust-Region Sequential Quadratic Programming for Equality-Constrained Optimization Problems [62.83783246648714]
  We propose a sequential quadratic programming algorithm (TR-StoSQP) to solve nonlinear optimization problems with objectives and deterministic equality constraints. The algorithm adaptively selects the trust-region radius and, compared to the existing line-search StoSQP schemes, allows us to utilize indefinite Hessian matrices.
  arXiv  Detail & Related papers  (2022-11-29T05:52:17Z)
• Optimal variance-reduced stochastic approximation in Banach spaces [114.8734960258221]
  We study the problem of estimating the fixed point of a contractive operator defined on a separable Banach space. We establish non-asymptotic bounds for both the operator defect and the estimation error.
  arXiv  Detail & Related papers  (2022-01-21T02:46:57Z)
• Integrated Conditional Estimation-Optimization [6.037383467521294]
  Many real-world optimization problems uncertain parameters with probability can be estimated using contextual feature information. In contrast to the standard approach of estimating the distribution of uncertain parameters, we propose an integrated conditional estimation approach. We show that our ICEO approach is theally consistent under moderate conditions.
  arXiv  Detail & Related papers  (2021-10-24T04:49:35Z)
• Linear-Time Probabilistic Solutions of Boundary Value Problems [27.70274403550477]
  We introduce a Gauss--Markov prior and tailor it specifically to BVPs. This allows computing a posterior distribution over the solution in linear time, at a quality and cost comparable to that of well-established, non-probabilistic methods.
  arXiv  Detail & Related papers  (2021-06-14T21:19:17Z)
• Optimal oracle inequalities for solving projected fixed-point equations [53.31620399640334]
  We study methods that use a collection of random observations to compute approximate solutions by searching over a known low-dimensional subspace of the Hilbert space. We show how our results precisely characterize the error of a class of temporal difference learning methods for the policy evaluation problem with linear function approximation.
  arXiv  Detail & Related papers  (2020-12-09T20:19:32Z)
• High-Dimensional Robust Mean Estimation via Gradient Descent [73.61354272612752]
  We show that the problem of robust mean estimation in the presence of a constant adversarial fraction can be solved by gradient descent. Our work establishes an intriguing connection between the near non-lemma estimation and robust statistics.
  arXiv  Detail & Related papers  (2020-05-04T10:48:04Z)

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.