Consequences of Optimality

• URL: http://arxiv.org/abs/2111.10861v2
• Date: Sat, 17 Jun 2023 14:43:11 GMT
• Title: Consequences of Optimality
• Authors: Dibakar Das
• Abstract summary: 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.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Rationality is often related to optimal decision making. Humans are known to be bounded rational agents. However, 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. In this paper, results from a computational model show that as more agents reach global optimality, faster with enhanced computing, etc., solving the same problem independently, this leads to accelerated "tragedy of the commons" due to quicker resource consumption. Thus, bounded rationality could be seen as blessing in disguise (providing diversity to solutions for the same problem) from sustainability standpoint.

Related papers

• The World Is Bigger! A Computationally-Embedded Perspective on the Big World Hypothesis [40.015199580592174]
  We describe a problem setting in which an agent, regardless of its capacity, is constrained by being embedded in the environment.<n>We propose an objective for this setting, which we call interactivity, that measures an agent's ability to continually adapt its behaviour by learning new predictions.<n>Our results show that deep nonlinear networks struggle to sustain interactivity, whereas deep linear networks sustain higher interactivity as capacity increases.
  arXiv  Detail & Related papers  (2025-12-29T12:31:46Z)
• Hype, Sustainability, and the Price of the Bigger-is-Better Paradigm in AI [67.58673784790375]
  We argue that the 'bigger is better' AI paradigm is not only fragile scientifically, but comes with undesirable consequences. First, it is not sustainable, as its compute demands increase faster than model performance, leading to unreasonable economic requirements and a disproportionate environmental footprint. Second, it implies focusing on certain problems at the expense of others, leaving aside important applications, e.g. health, education, or the climate.
  arXiv  Detail & Related papers  (2024-09-21T14:43:54Z)
• Successive Refinement in Large-Scale Computation: Advancing Model Inference Applications [67.76749044675721]
  We introduce solutions for layered-resolution computation. These solutions allow lower-resolution results to be obtained at an earlier stage than the final result.
  arXiv  Detail & Related papers  (2024-02-11T15:36:33Z)
• 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)
• Neural Amortized Inference for Nested Multi-agent Reasoning [54.39127942041582]
  We propose a novel approach to bridge the gap between human-like inference capabilities and computational limitations. We evaluate our method in two challenging multi-agent interaction domains.
  arXiv  Detail & Related papers  (2023-08-21T22:40:36Z)
• Computability of Optimizers [71.84486326350338]
  We will show that in various situations the is unattainable on Turing machines and consequently on digital computers. We prove such results for a variety of well-known problems from very different areas, including artificial intelligence, financial mathematics, and information theory.
  arXiv  Detail & Related papers  (2023-01-15T17:41:41Z)
• Decision-Making Among Bounded Rational Agents [5.24482648010213]
  We introduce the concept of bounded rationality from an information-theoretic view into the game-theoretic framework. This allows the robots to reason other agents' sub-optimal behaviors and act accordingly under their computational constraints. We demonstrate that the resulting framework allows the robots to reason about different levels of rational behaviors of other agents and compute a reasonable strategy under its computational constraint.
  arXiv  Detail & Related papers  (2022-10-17T00:29:24Z)
• Rationality in current era -- A recent survey [0.0]
  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.
  arXiv  Detail & Related papers  (2022-04-27T12:09:41Z)
• Learning Human Rewards by Inferring Their Latent Intelligence Levels in Multi-Agent Games: A Theory-of-Mind Approach with Application to Driving Data [18.750834997334664]
  We argue that humans are bounded rational and have different intelligence levels when reasoning about others' decision-making process. We propose a new multi-agent Inverse Reinforcement Learning framework that reasons about humans' latent intelligence levels during learning.
  arXiv  Detail & Related papers  (2021-03-07T07:48:31Z)
• From Checking to Inference: Actual Causality Computations as Optimization Problems [79.87179017975235]
  We present a novel approach to formulate different notions of causal reasoning, over binary acyclic models, as optimization problems. We show that both notions are efficiently automated. Using models with more than $8000$ variables, checking is computed in a matter of seconds, with MaxSAT outperforming ILP in many cases.
  arXiv  Detail & Related papers  (2020-06-05T10:56:52Z)
• 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.