Reward is not enough: can we liberate AI from the reinforcement learning paradigm?

• URL: http://arxiv.org/abs/2202.03192v3
• Date: Mon, 11 Nov 2024 09:34:57 GMT
• Title: Reward is not enough: can we liberate AI from the reinforcement learning paradigm?
• Authors: Vacslav Glukhov,
• Abstract summary: Reward is not enough to explain many activities associated with natural and artificial intelligence. Complexities of intelligent behaviour are not simply second-order complications on top of reward maximisation.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: I present arguments against the hypothesis put forward by Silver, Singh, Precup, and Sutton ( https://www.sciencedirect.com/science/article/pii/S0004370221000862 ) : reward maximization is not enough to explain many activities associated with natural and artificial intelligence including knowledge, learning, perception, social intelligence, evolution, language, generalisation and imitation. I show such reductio ad lucrum has its intellectual origins in the political economy of Homo economicus and substantially overlaps with the radical version of behaviourism. I show why the reinforcement learning paradigm, despite its demonstrable usefulness in some practical application, is an incomplete framework for intelligence -- natural and artificial. Complexities of intelligent behaviour are not simply second-order complications on top of reward maximisation. This fact has profound implications for the development of practically usable, smart, safe and robust artificially intelligent agents.

Related papers

• Bridging Minds and Machines: Toward an Integration of AI and Cognitive Science [48.38628297686686]
  Cognitive Science has profoundly shaped disciplines such as Artificial Intelligence (AI), Philosophy, Psychology, Neuroscience, Linguistics, and Culture.<n>Many breakthroughs in AI trace their roots to cognitive theories, while AI itself has become an indispensable tool for advancing cognitive research.<n>We argue that the future of AI within Cognitive Science lies not only in improving performance but also in constructing systems that deepen our understanding of the human mind.
  arXiv  Detail & Related papers  (2025-08-28T11:26:17Z)
• Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence [59.07578850674114]
  Sound deductive reasoning is an indisputably desirable aspect of general intelligence.<n>It is well-documented that even the most advanced frontier systems regularly and consistently falter on easily-solvable reasoning tasks.<n>We argue that their unsound behavior is a consequence of the statistical learning approach powering their development.
  arXiv  Detail & Related papers  (2025-06-30T14:37:50Z)
• Evaluating Intelligence via Trial and Error [59.80426744891971]
  We introduce Survival Game as a framework to evaluate intelligence based on the number of failed attempts in a trial-and-error process. When the expectation and variance of failure counts are both finite, it signals the ability to consistently find solutions to new challenges. Our results show that while AI systems achieve the Autonomous Level in simple tasks, they are still far from it in more complex tasks.
  arXiv  Detail & Related papers  (2025-02-26T05:59:45Z)
• Imagining and building wise machines: The centrality of AI metacognition [78.76893632793497]
  We argue that shortcomings stem from one overarching failure: AI systems lack wisdom. While AI research has focused on task-level strategies, metacognition is underdeveloped in AI systems. We propose that integrating metacognitive capabilities into AI systems is crucial for enhancing their robustness, explainability, cooperation, and safety.
  arXiv  Detail & Related papers  (2024-11-04T18:10:10Z)
• Spontaneous Theory of Mind for Artificial Intelligence [2.7624021966289605]
  We argue for a principled approach to studying and developing AI Theory of Mind (ToM) We suggest that a robust, or general, ASI will respond to prompts textitand spontaneously engage in social reasoning.
  arXiv  Detail & Related papers  (2024-02-16T22:41:13Z)
• On a Functional Definition of Intelligence [0.0]
  Without an agreed-upon definition of intelligence, asking "is this system intelligent?"" is an untestable question. Most work on precisely capturing what we mean by "intelligence" has come from the fields of philosophy, psychology, and cognitive science. We present an argument for a purely functional, black-box definition of intelligence, distinct from how that intelligence is actually achieved.
  arXiv  Detail & Related papers  (2023-12-15T05:46:49Z)
• Enabling High-Level Machine Reasoning with Cognitive Neuro-Symbolic Systems [67.01132165581667]
  We propose to enable high-level reasoning in AI systems by integrating cognitive architectures with external neuro-symbolic components. We illustrate a hybrid framework centered on ACT-R and we discuss the role of generative models in recent and future applications.
  arXiv  Detail & Related papers  (2023-11-13T21:20:17Z)
• The Generative AI Paradox: "What It Can Create, It May Not Understand" [81.89252713236746]
  Recent wave of generative AI has sparked excitement and concern over potentially superhuman levels of artificial intelligence. At the same time, models still show basic errors in understanding that would not be expected even in non-expert humans. This presents us with an apparent paradox: how do we reconcile seemingly superhuman capabilities with the persistence of errors that few humans would make?
  arXiv  Detail & Related papers  (2023-10-31T18:07:07Z)
• From Psychological Curiosity to Artificial Curiosity: Curiosity-Driven Learning in Artificial Intelligence Tasks [56.20123080771364]
  Psychological curiosity plays a significant role in human intelligence to enhance learning through exploration and information acquisition. In the Artificial Intelligence (AI) community, artificial curiosity provides a natural intrinsic motivation for efficient learning. CDL has become increasingly popular, where agents are self-motivated to learn novel knowledge.
  arXiv  Detail & Related papers  (2022-01-20T17:07:03Z)
• Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021) [5.377016988002648]
  We argue that scalar rewards are insufficient to account for some aspects of both biological and computational intelligence. It is still undesirable to use this approach for the development of artificial general intelligence due to unacceptable risks of unsafe or unethical behaviour.
  arXiv  Detail & Related papers  (2021-11-25T00:58:23Z)
• 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)
• Future Trends for Human-AI Collaboration: A Comprehensive Taxonomy of AI/AGI Using Multiple Intelligences and Learning Styles [95.58955174499371]
  We describe various aspects of multiple human intelligences and learning styles, which may impact on a variety of AI problem domains. Future AI systems will be able not only to communicate with human users and each other, but also to efficiently exchange knowledge and wisdom.
  arXiv  Detail & Related papers  (2020-08-07T21:00:13Z)
• Dynamic Cognition Applied to Value Learning in Artificial Intelligence [0.0]
  Several researchers in the area are trying to develop a robust, beneficial, and safe concept of artificial intelligence. It is of utmost importance that artificial intelligent agents have their values aligned with human values. A possible approach to this problem would be to use theoretical models such as SED.
  arXiv  Detail & Related papers  (2020-05-12T03:58:52Z)
• Is Intelligence Artificial? [0.0]
  This paper attempts to give a unifying definition that can be applied to the natural world in general and then Artificial Intelligence. A metric that is grounded in Kolmogorov's Complexity Theory is suggested, which leads to a measurement about entropy. A version of an accepted AI test is then put forward as the 'acid test' and might be what a free-thinking program would try to achieve.
  arXiv  Detail & Related papers  (2014-03-05T11:09:55Z)

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.