How to Choose a Reinforcement-Learning Algorithm

• URL: http://arxiv.org/abs/2407.20917v1
• Date: Tue, 30 Jul 2024 15:54:18 GMT
• Title: How to Choose a Reinforcement-Learning Algorithm
• Authors: Fabian Bongratz, Vladimir Golkov, Lukas Mautner, Luca Della Libera, Frederik Heetmeyer, Felix Czaja, Julian Rodemann, Daniel Cremers,
• Abstract summary: We streamline the process of choosing reinforcement-learning algorithms and action-distribution families. We provide a structured overview of existing methods and their properties, as well as guidelines for when to choose which methods.
• Score: 29.76033485145459
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The field of reinforcement learning offers a large variety of concepts and methods to tackle sequential decision-making problems. This variety has become so large that choosing an algorithm for a task at hand can be challenging. In this work, we streamline the process of choosing reinforcement-learning algorithms and action-distribution families. We provide a structured overview of existing methods and their properties, as well as guidelines for when to choose which methods. An interactive version of these guidelines is available online at https://rl-picker.github.io/.

Related papers

• Interactively Teaching an Inverse Reinforcement Learner with Limited Feedback [4.174296652683762]
  We study the problem of teaching via demonstrations in sequential decision-making tasks. In this work, we formalize the teaching process with limited feedback and propose an algorithm that solves this problem.
  arXiv  Detail & Related papers  (2023-09-16T21:12:04Z)
• Explainable Data-Driven Optimization: From Context to Decision and Back Again [76.84947521482631]
  Data-driven optimization uses contextual information and machine learning algorithms to find solutions to decision problems with uncertain parameters. We introduce a counterfactual explanation methodology tailored to explain solutions to data-driven problems. We demonstrate our approach by explaining key problems in operations management such as inventory management and routing.
  arXiv  Detail & Related papers  (2023-01-24T15:25:16Z)
• Reusable Options through Gradient-based Meta Learning [24.59017394648942]
  Several deep learning approaches were proposed to learn temporal abstractions in the form of options in an end-to-end manner. We frame the problem of learning options as a gradient-based meta-learning problem. We show that our method is able to learn transferable components which accelerate learning and performs better than existing prior methods.
  arXiv  Detail & Related papers  (2022-12-22T14:19:35Z)
• The Paradox of Choice: Using Attention in Hierarchical Reinforcement Learning [59.777127897688594]
  We present an online, model-free algorithm to learn affordances that can be used to further learn subgoal options. We investigate the role of hard versus soft attention in training data collection, abstract value learning in long-horizon tasks, and handling a growing number of choices.
  arXiv  Detail & Related papers  (2022-01-24T13:18:02Z)
• Branch and Bound in Mixed Integer Linear Programming Problems: A Survey of Techniques and Trends [7.432176855020725]
  We study different approaches and algorithms for the four critical components in the general branch and bound (B&B) algorithm. In order to improve the speed of B&B algorithms, learning techniques have been introduced in this algorithm recently.
  arXiv  Detail & Related papers  (2021-11-05T10:18:21Z)
• Algorithm Selection on a Meta Level [58.720142291102135]
  We introduce the problem of meta algorithm selection, which essentially asks for the best way to combine a given set of algorithm selectors. We present a general methodological framework for meta algorithm selection as well as several concrete learning methods as instantiations of this framework.
  arXiv  Detail & Related papers  (2021-07-20T11:23:21Z)
• Reinforcement Learning as Iterative and Amortised Inference [62.997667081978825]
  We use the control as inference framework to outline a novel classification scheme based on amortised and iterative inference. We show that taking this perspective allows us to identify parts of the algorithmic design space which have been relatively unexplored.
  arXiv  Detail & Related papers  (2020-06-13T16:10:03Z)
• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems [108.81683598693539]
  offline reinforcement learning algorithms hold tremendous promise for making it possible to turn large datasets into powerful decision making engines. We will aim to provide the reader with an understanding of these challenges, particularly in the context of modern deep reinforcement learning methods.
  arXiv  Detail & Related papers  (2020-05-04T17:00:15Z)
• Learning with Differentiable Perturbed Optimizers [54.351317101356614]
  We propose a systematic method to transform operations into operations that are differentiable and never locally constant. Our approach relies on perturbeds, and can be used readily together with existing solvers. We show how this framework can be connected to a family of losses developed in structured prediction, and give theoretical guarantees for their use in learning tasks.
  arXiv  Detail & Related papers  (2020-02-20T11:11:32Z)
• Online Preselection with Context Information under the Plackett-Luce Model [10.286111512725334]
  We consider an extension of the contextual multi-armed bandit problem. Instead of selecting a single alternative (arm), a learner is supposed to make a preselection in the form of a subset of alternatives. We propose the CPPL algorithm, which is inspired by the well-known UCB algorithm.
  arXiv  Detail & Related papers  (2020-02-11T09:27:24Z)

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.