Rationality in current era -- A recent survey

• URL: http://arxiv.org/abs/2204.12872v1
• Date: Wed, 27 Apr 2022 12:09:41 GMT
• Title: Rationality in current era -- A recent survey
• Authors: Dibakar Das
• Abstract summary: The paper attempts to put forward a recent survey (last five years) of research on divergent views on rationality. The first school is sceptical of progress of AI and believes that human intelligencewill always supersede machine intelligence. The second school thinks that advent of AI and advances in computing will help in better understanding of bounded rationality.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Rationality has been an intriguing topic for several decades. Even the scope of definition of rationality across different subjects varies. Several theories (e.g., game theory) initially evolved on the basis that agents (e.g., humans) are perfectly rational. One interpretation of perfect rationality is that agents always make the optimal decision which maximizes their expected utilities. However, subsequently this assumption was relaxed to include bounded rationality where agents have limitations in terms of computing resources and biases which prevents them to take the optimal decision. However, with recent advances in (quantum) computing, artificial intelligence (AI), science and technology etc., has led to the thought that perhaps the concept of rationality would be augmented with machine intelligence which will enable agents to take decision optimally with higher regularity. However, there are divergent views on this topic. The paper attempts to put forward a recent survey (last five years) of research on these divergent views. These viewsmay be grouped into three schools of thoughts. The first school is the one which is sceptical of progress of AI and believes that human intelligencewill always supersede machine intelligence. The second school of thought thinks that advent of AI and advances in computing will help in better understanding of bounded rationality. Third school of thought believes that bounds of bounded rationality will be extended by advances in AI and various other fields. This survey hopes to provide a starting point for further research.

Related papers

• Machine learning and information theory concepts towards an AI Mathematician [77.63761356203105]
  The current state-of-the-art in artificial intelligence is impressive, especially in terms of mastery of language, but not so much in terms of mathematical reasoning. This essay builds on the idea that current deep learning mostly succeeds at system 1 abilities. It takes an information-theoretical posture to ask questions about what constitutes an interesting mathematical statement.
  arXiv  Detail & Related papers  (2024-03-07T15:12:06Z)
• Position Paper: Agent AI Towards a Holistic Intelligence [53.35971598180146]
  We emphasize developing Agent AI -- an embodied system that integrates large foundation models into agent actions. In this paper, we propose a novel large action model to achieve embodied intelligent behavior, the Agent Foundation Model.
  arXiv  Detail & Related papers  (2024-02-28T16:09:56Z)
• (Ir)rationality in AI: State of the Art, Research Challenges and Open Questions [2.9008806248012333]
  The concept of rationality is central to the field of artificial intelligence. There is no unified definition of what constitutes a rational agent. We consider irrational behaviours that can prove to be optimal in certain scenarios.
  arXiv  Detail & Related papers  (2023-11-28T19:01:09Z)
• Several Consequences of Optimality [0.43512163406552007]
  Findings from a computational model demonstrated that when an increasing number of agents independently strive to achieve global optimality, facilitated by improved computing power, they indirectly accelerated the occurrence of the "tragedy of the commons" As agents achieve optimality, there is a drop in information entropy among the solutions of the agents. Two groups, one as producer and the other (the group agents searching for optimality) as consumer of the highest consumed resource, seem to gain more than the producers.
  arXiv  Detail & Related papers  (2023-11-02T11:33:51Z)
• AI for Mathematics: A Cognitive Science Perspective [86.02346372284292]
  Mathematics is one of the most powerful conceptual systems developed and used by the human species. Rapid progress in AI, particularly propelled by advances in large language models (LLMs), has sparked renewed, widespread interest in building such systems.
  arXiv  Detail & Related papers  (2023-10-19T02:00:31Z)
• A Theory of Bounded Inductive Rationality [0.0]
  We develop a theory of rational decision making that does not assume logical omniscience. We consider agents who repeatedly face decision problems, including ones like betting on digits of pi. We prove that agents that are rational in this sense have other desirable properties.
  arXiv  Detail & Related papers  (2023-07-11T07:13:29Z)
• Exploring the Constraints on Artificial General Intelligence: A Game-Theoretic No-Go Theorem [0.0]
  I propose a game-theoretic framework that captures the strategic interactions between a human agent and a potential superhuman machine agent. My analysis contributes to a better understanding of the context that can shape the theoretical development of superhuman AI.
  arXiv  Detail & Related papers  (2022-09-25T23:17:20Z)
• Consequences of Optimality [0.0]
  Humans are known to be bounded rational agents. Recent advances in computing, and other scientific and technical fields along with large amount of data have led to a feeling that this could result in extending the limits of bounded rationality in humans through augmented machine intelligence.
  arXiv  Detail & Related papers  (2021-11-21T17:05:22Z)
• Automated Machine Learning, Bounded Rationality, and Rational Metareasoning [62.997667081978825]
  We will look at automated machine learning (AutoML) and related problems from the perspective of bounded rationality. Taking actions under bounded resources requires an agent to reflect on how to use these resources in an optimal way.
  arXiv  Detail & Related papers  (2021-09-10T09:10:20Z)
• Inductive Biases for Deep Learning of Higher-Level Cognition [108.89281493851358]
  A fascinating hypothesis is that human and animal intelligence could be explained by a few principles. This work considers a larger list, focusing on those which concern mostly higher-level and sequential conscious processing. The objective of clarifying these particular principles is that they could potentially help us build AI systems benefiting from humans' abilities.
  arXiv  Detail & Related papers  (2020-11-30T18:29:25Z)
• 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.