Universal Imitation Games

• URL: http://arxiv.org/abs/2405.01540v1
• Date: Fri, 2 Feb 2024 00:07:15 GMT
• Title: Universal Imitation Games
• Authors: Sridhar Mahadevan,
• Abstract summary: We analyze a broader class of universal imitation games (UIGs) We use the framework of category theory to characterize each type of imitation game. We briefly discuss the extension of our categorical framework for UIGs to imitation games on quantum computers.
• Score: 3.0316063849624477
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Alan Turing proposed in 1950 a framework called an imitation game to decide if a machine could think. Using mathematics developed largely after Turing -- category theory -- we analyze a broader class of universal imitation games (UIGs), which includes static, dynamic, and evolutionary games. In static games, the participants are in a steady state. In dynamic UIGs, "learner" participants are trying to imitate "teacher" participants over the long run. In evolutionary UIGs, the participants are competing against each other in an evolutionary game, and participants can go extinct and be replaced by others with higher fitness. We use the framework of category theory -- in particular, two influential results by Yoneda -- to characterize each type of imitation game. Universal properties in categories are defined by initial and final objects. We characterize dynamic UIGs where participants are learning by inductive inference as initial algebras over well-founded sets, and contrast them with participants learning by conductive inference over the final coalgebra of non-well-founded sets. We briefly discuss the extension of our categorical framework for UIGs to imitation games on quantum computers.

Related papers

• Unbounded: A Generative Infinite Game of Character Life Simulation [68.37260000219479]
  We introduce the concept of a generative infinite game, a video game that transcends the traditional boundaries of finite, hard-coded systems by using generative models. We leverage recent advances in generative AI to create Unbounded: a game of character life simulation that is fully encapsulated in generative models.
  arXiv  Detail & Related papers  (2024-10-24T17:59:31Z)
• Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation [51.750634349748736]
  Text-to-video (T2V) models have made significant strides in visualizing complex prompts. However, the capacity of these models to accurately represent intuitive physics remains largely unexplored. We introduce PhyGenBench to evaluate physical commonsense correctness in T2V generation.
  arXiv  Detail & Related papers  (2024-10-07T17:56:04Z)
• The Participation Game [0.0]
  Inspired by Turing's famous "imitation game," we pose the participation game to point to a new frontier in AI evolution. The participation game is a creative, playful competition that calls for applying, bending, and stretching the categories humans use to make sense of and order their worlds.
  arXiv  Detail & Related papers  (2023-04-25T10:07:13Z)
• On the Convergence of No-Regret Learning Dynamics in Time-Varying Games [89.96815099996132]
  We characterize the convergence of optimistic gradient descent (OGD) in time-varying games. Our framework yields sharp convergence bounds for the equilibrium gap of OGD in zero-sum games. We also provide new insights on dynamic regret guarantees in static games.
  arXiv  Detail & Related papers  (2023-01-26T17:25:45Z)
• Dynamic Operads, Dynamic Categories: From Deep Learning to Prediction Markets [0.0]
  We show how dynamic categorical structures instantiate the motivating philosophical ideas. We give two examples of dynamic categorical structures: prediction markets as a dynamic operad and deep learning as a dynamic monoidal category.
  arXiv  Detail & Related papers  (2022-05-08T16:16:44Z)
• No-Regret Learning in Games is Turing Complete [33.03065693224728]
  We prove Turing completeness of the replicator dynamic on matrix games, one of the simplest possible settings. Our results imply the undecicability of reachability problems for learning algorithms in games, a special case of which is determining equilibrium convergence.
  arXiv  Detail & Related papers  (2022-02-24T02:37:50Z)
• Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning [109.21780441933164]
  We propose a hybrid approach to improve systematic generalization in reasoning. We showcase a prototype with algebraic representation for the abstract spatial-temporal task of Raven's Progressive Matrices (RPM) We show that the algebraic representation learned can be decoded by isomorphism to generate an answer.
  arXiv  Detail & Related papers  (2021-11-25T09:56:30Z)
• Learning in nonatomic games, Part I: Finite action spaces and population games [22.812059396480656]
  We examine the long-run behavior of a wide range of dynamics for learning in nonatomic games, in both discrete and continuous time. We focus exclusively on games with finite action spaces; nonatomic games with continuous action spaces are treated in detail in Part II of this paper.
  arXiv  Detail & Related papers  (2021-07-04T11:20:45Z)
• Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games [27.510231246176033]
  This paper introduces and analyze a class of competitive settings where both the agents and the games they play evolve strategically over time. Populations of agents compete against each other in a zero-sum competition that itself evolves adversarially to the current population mixture. Remarkably, despite the chaotic coevolution of agents and games, we prove that the system exhibits a number of regularities.
  arXiv  Detail & Related papers  (2020-12-15T15:54:46Z)
• Imagining Grounded Conceptual Representations from Perceptual Information in Situated Guessing Games [83.53942719040576]
  In visual guessing games, a Guesser has to identify a target object in a scene by asking questions to an Oracle. Existing models fail to learn truly multi-modal representations, relying instead on gold category labels for objects in the scene both at training and inference time. We introduce a novel "imagination" module based on Regularized Auto-Encoders, that learns context-aware and category-aware latent embeddings without relying on category labels at inference time.
  arXiv  Detail & Related papers  (2020-11-05T15:42:29Z)
• Universal-to-Specific Framework for Complex Action Recognition [114.78468658086572]
  We propose an effective universal-to-specific (U2S) framework for complex action recognition. The U2S framework is composed of threeworks: a universal network, a category-specific network, and a mask network. Experiments on a variety of benchmark datasets demonstrate the effectiveness of the U2S framework.
  arXiv  Detail & Related papers  (2020-07-13T01:49:07Z)

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.