Functional Decision Theory in an Evolutionary Environment

• URL: http://arxiv.org/abs/2005.05154v2
• Date: Mon, 26 Apr 2021 16:59:57 GMT
• Title: Functional Decision Theory in an Evolutionary Environment
• Authors: Noah Topper
• Abstract summary: Functional decision theory (FDT) is a fairly new mode of decision theory and a normative viewpoint on how an agent should maximize expected utility. The current standard in decision theory and computer science is causal decision theory (CDT), largely seen as superior to the main alternative evidential decision theory (EDT)
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Functional decision theory (FDT) is a fairly new mode of decision theory and a normative viewpoint on how an agent should maximize expected utility. The current standard in decision theory and computer science is causal decision theory (CDT), largely seen as superior to the main alternative evidential decision theory (EDT). These theories prescribe three distinct methods for maximizing utility. We explore how FDT differs from CDT and EDT, and what implications it has on the behavior of FDT agents and humans. It has been shown in previous research how FDT can outperform CDT and EDT. We additionally show FDT performing well on more classical game theory problems and argue for its extension to human problems to show that its potential for superiority is robust. We also make FDT more concrete by displaying it in an evolutionary environment, competing directly against other theories.

Related papers

• Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence [53.51724434972605]
  This paper theoretically answers the key factors that contribute to the generalization gap when the testing environment has distractors. Our theories indicate that minimizing the representation distance between training and testing environments, which aligns with human intuition, is the most critical for the benefit of reducing the generalization gap.
  arXiv  Detail & Related papers  (2024-02-05T03:27:52Z)
• Sherlock Holmes Doesn't Play Dice: The significance of Evidence Theory for the Social and Life Sciences [0.0]
  Evidence Theory can express the uncertainty deriving from the fear that events may materialize. Probability Theory must limit itself to the possibilities that a decision-maker is currently envisaging.
  arXiv  Detail & Related papers  (2023-09-01T07:52:28Z)
• Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories? [78.3738172874685]
  Making moral judgments is an essential step toward developing ethical AI systems. Prevalent approaches are mostly implemented in a bottom-up manner, which uses a large set of annotated data to train models based on crowd-sourced opinions about morality. This work proposes a flexible top-down framework to steer (Large) Language Models (LMs) to perform moral reasoning with well-established moral theories from interdisciplinary research.
  arXiv  Detail & Related papers  (2023-08-29T15:57:32Z)
• A Semantic Approach to Decidability in Epistemic Planning (Extended Version) [72.77805489645604]
  We use a novel semantic approach to achieve decidability. Specifically, we augment the logic of knowledge S5$_n$ and with an interaction axiom called (knowledge) commutativity. We prove that our framework admits a finitary non-fixpoint characterization of common knowledge, which is of independent interest.
  arXiv  Detail & Related papers  (2023-07-28T11:26:26Z)
• Characterising Decision Theories with Mechanised Causal Graphs [11.114498728830851]
  We show that mechanised causal models can be used to characterise and differentiate the most important decision theories. We generate a taxonomy of different decision theories.
  arXiv  Detail & Related papers  (2023-07-20T16:18:22Z)
• Typical perturbation theory: conditions, accuracy and comparison with a mesoscopic case [0.0]
  The perturbation theory based on typicality introduced in Ref. [1] and further refined in Refs. [2, 3] is tested on three spin-based models. The following criteria are taken into focus: the fulfillment of the conditions, the accuracy of the predicted dynamics and the relevance of the results with respect to a mesoscopic case.
  arXiv  Detail & Related papers  (2022-07-12T12:52:25Z)
• A Quantitative Symbolic Approach to Individual Human Reasoning [0.0]
  We take findings from the literature and show how these, formalized as cognitive principles within a logical framework, can establish a quantitative notion of reasoning. We employ techniques from non-monotonic reasoning and computer science, namely, a solving paradigm called answer set programming (ASP) Finally, we can fruitfully use plausibility reasoning in ASP to test the effects of an existing experiment and explain different majority responses.
  arXiv  Detail & Related papers  (2022-05-10T16:43:47Z)
• A Mathematical Walkthrough and Discussion of the Free Energy Principle [0.0]
  The Free-Energy-Principle (FEP) is an influential and controversial theory which postulates a connection between the thermodynamics of self-organization and learning through variational inference. FEP has been applied extensively in neuroscience, and is beginning to make inroads in machine learning by spurring the construction of novel and powerful algorithms by which action, perception, and learning can all be unified under a single objective. Here, we aim to provide a mathematically detailed, yet intuitive walk-through of the formulation and central claims of the FEP while also providing a discussion of the assumptions necessary and potential limitations of the theory.
  arXiv  Detail & Related papers  (2021-08-30T16:11:49Z)
• Transporting Causal Mechanisms for Unsupervised Domain Adaptation [98.67770293233961]
  We propose Transporting Causal Mechanisms (TCM) to identify the confounder stratum and representations. TCM achieves state-of-the-art performance on three challenging Unsupervised Domain Adaptation benchmarks.
  arXiv  Detail & Related papers  (2021-07-23T07:25:15Z)
• Perfect Discrimination in Approximate Quantum Theory of General Probabilistic Theories [51.7367238070864]
  We define larger measurement classes that are smoothly connected with the class of POVMs via a parameter. We give a sufficient condition of perfect discrimination, which shows a significant improvement beyond the class of POVMs.
  arXiv  Detail & Related papers  (2020-04-10T08:45:20Z)
• Invariant Rationalization [84.1861516092232]
  A typical rationalization criterion, i.e. maximum mutual information (MMI), finds the rationale that maximizes the prediction performance based only on the rationale. We introduce a game-theoretic invariant rationalization criterion where the rationales are constrained to enable the same predictor to be optimal across different environments. We show both theoretically and empirically that the proposed rationales can rule out spurious correlations, generalize better to different test scenarios, and align better with human judgments.
  arXiv  Detail & Related papers  (2020-03-22T00:50:27Z)

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.