Inference with Choice Functions Made Practical

• URL: http://arxiv.org/abs/2005.03098v3
• Date: Wed, 15 Jul 2020 14:08:00 GMT
• Title: Inference with Choice Functions Made Practical
• Authors: Arne Decadt, Jasper De Bock, Gert de Cooman
• Abstract summary: We study how to infer new choices from previous choices in a conservative manner. We use the theory of choice functions: a unifying mathematical framework for conservative decision making.
• Score: 1.1859913430860332
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study how to infer new choices from previous choices in a conservative manner. To make such inferences, we use the theory of choice functions: a unifying mathematical framework for conservative decision making that allows one to impose axioms directly on the represented decisions. We here adopt the coherence axioms of De Bock and De Cooman (2019). We show how to naturally extend any given choice assessment to such a coherent choice function, whenever possible, and use this natural extension to make new choices. We present a practical algorithm to compute this natural extension and provide several methods that can be used to improve its scalability.

Related papers

• Extending choice assessments to choice functions: An algorithm for computing the natural extension [45.238324742678124]
  We study how to infer new choices from prior choices using the framework of choice functions. In particular, we define the natural (most conservative) extension of a given choice assessment to a coherent choice function.
  arXiv  Detail & Related papers  (2024-07-30T20:10:59Z)
• Decision-making with E-admissibility given a finite assessment of choices [64.29961886833972]
  We study the implications for decision-making with E-admissibility. We use the mathematical framework of choice functions to specify choices and rejections. We provide an algorithm that computes this extension by solving linear feasibility problems.
  arXiv  Detail & Related papers  (2022-04-15T11:46:00Z)
• Choosing on Sequences [0.0]
  We propose a new framework that considers choice from infinite sequences. We show that bounded attention is due to the continuity of the choice functions with respect to a natural topology. We introduce the notion of computability of a choice function using Turing machines and show that computable choice rules can be implemented by a finite automaton.
  arXiv  Detail & Related papers  (2022-02-28T20:16:24Z)
• Temporal Abstraction in Reinforcement Learning with the Successor Representation [65.69658154078007]
  We argue that the successor representation (SR) can be seen as a natural substrate for the discovery and use of temporal abstractions. We show how the SR can be used to discover options that facilitate either temporally-extended exploration or planning.
  arXiv  Detail & Related papers  (2021-10-12T05:07:43Z)
• Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment [79.5678820246642]
  We show that certain action-value methods are more sample efficient than policy-gradient methods on transfer problems that require only sparse changes to a sequence of previously optimal decisions. We generalize the recently proposed societal decision-making framework as a more granular formalism than the Markov decision process.
  arXiv  Detail & Related papers  (2021-06-28T21:29:13Z)
• Adversarial Option-Aware Hierarchical Imitation Learning [89.92994158193237]
  We propose Option-GAIL, a novel method to learn skills at long horizon. The key idea of Option-GAIL is modeling the task hierarchy by options and train the policy via generative adversarial optimization. Experiments show that Option-GAIL outperforms other counterparts consistently across a variety of tasks.
  arXiv  Detail & Related papers  (2021-06-10T06:42:05Z)
• Smart Choices and the Selection Monad [0.0]
  Describing systems in terms of choices and their resulting costs and rewards offers the promise of freeing algorithm designers and programmers from specifying how those choices should be made. We define two small languages that support decision-making abstractions: one with choices and rewards, and the other additionally with probabilities.
  arXiv  Detail & Related papers  (2020-07-17T12:13:16Z)
• Learning Choice Functions via Pareto-Embeddings [3.1410342959104725]
  We consider the problem of learning to choose from a given set of objects, where each object is represented by a feature vector. We propose a learning algorithm that minimizes a differentiable loss function suitable for this task.
  arXiv  Detail & Related papers  (2020-07-14T09:34:44Z)
• Archimedean Choice Functions: an Axiomatic Foundation for Imprecise Decision Making [0.9442139459221782]
  We focus on two generalisations that apply to sets of probability measures: E-admissibility and maximality. We provide a set of necessary and sufficient conditions on choice functions that uniquely characterises this rule. A representation theorem for Archimedean choice functions in terms of coherent lower previsions lies at the basis of both results.
  arXiv  Detail & Related papers  (2020-02-12T19:44:08Z)
• Options of Interest: Temporal Abstraction with Interest Functions [58.30081828754683]
  We provide a generalization of initiation sets suitable for general function approximation, by defining an interest function associated with an option. We derive a gradient-based learning algorithm for interest functions, leading to a new interest-option-critic architecture.
  arXiv  Detail & Related papers  (2020-01-01T21:24:39Z)

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.