The application of temporal difference learning in optimal diet models

Teichmann, Jan; Broom, Mark; Alonso, Eduardo

doi:10.1016/j.jtbi.2013.08.036

Cited by 3 publications

(1 citation statement)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typically, optimal behaviour has been assumed to result from natural selection of genetically determined behaviour strategies [4], yet in many species behaviour is crucially shaped by individual experiences and learning [5][6][7]. Existing work has considered how learning can optimize single responses [8][9][10][11][12][13] or specific sequences of two or three behaviours [14,15]. However, the question of how, and how much, learning contributes to optimal behaviour is still largely open.…”

Section: Introductionmentioning

confidence: 99%

The power of associative learning and the ontogeny of optimal behaviour

2016

View full text Add to dashboard Cite

Behaving efficiently (optimally or near-optimally) is central to animals' adaptation to their environment. Much evolutionary biology assumes, implicitly or explicitly, that optimal behavioural strategies are genetically inherited, yet the behaviour of many animals depends crucially on learning. The question of how learning contributes to optimal behaviour is largely open. Here we propose an associative learning model that can learn optimal behaviour in a wide variety of ecologically relevant circumstances. The model learns through chaining, a term introduced by Skinner to indicate learning of behaviour sequences by linking together shorter sequences or single behaviours. Our model formalizes the concept of conditioned reinforcement (the learning process that underlies chaining) and is closely related to optimization algorithms from machine learning. Our analysis dispels the common belief that associative learning is too limited to produce ‘intelligent’ behaviour such as tool use, social learning, self-control or expectations of the future. Furthermore, the model readily accounts for both instinctual and learned aspects of behaviour, clarifying how genetic evolution and individual learning complement each other, and bridging a long-standing divide between ethology and psychology. We conclude that associative learning, supported by genetic predispositions and including the oft-neglected phenomenon of conditioned reinforcement, may suffice to explain the ontogeny of optimal behaviour in most, if not all, non-human animals. Our results establish associative learning as a more powerful optimizing mechanism than acknowledged by current opinion.

show abstract

Section: Introductionmentioning

confidence: 99%

The power of associative learning and the ontogeny of optimal behaviour

2016

View full text Add to dashboard Cite

show abstract

Comprehensive Survey of Machine Learning Approaches in Cognitive Radio-Based Vehicular Ad Hoc Networks

et al. 2020

View full text Add to dashboard Cite

Nowadays, machine learning (ML), which is one of the most rapidly growing technical tools, is extensively used to solve critical challenges in various domains. Vehicular ad hoc network (VANET) is expected to be the key role player in reducing road casualties and traffic congestion. To ensure this role, a gigantic amount of data should be exchanged. However, current allocated wireless access for VANET is inadequate to handle such massive data amounts. Therefore, VANET faces a spectrum scarcity issue. Cognitive radio (CR) is a promising solution to overcome such an issue. CR-based VANET or CR-VANET must achieve several performance enhancement measures, including ultra-reliable and lowlatency communication. ML methods can be integrated with CR-VANET to make CR-VANET highly intelligent, achieve rapid adaptability to the dynamicity of the environment, and improve the quality of service in an energy-efficient manner. This paper presents an overview of ML, CR, VANET, and CR-VANET, including their architectures, functions, challenges, and open issues. The applications and roles of ML methods in CR-VANET scenarios are reviewed. Insights into the use of ML for autonomous or driverless vehicles are also presented. Current advancements in the amalgamation of these prominent technologies and future research directions are discussed. INDEX TERMS Machine learning, VANET, cognitive radio, autonomous vehicles, smart transportation system. performance of CR-VANET [15]. Security enhancement is one of the major issues in CR-VANET. Here, a vehicle can pretend to be a PU and propagate false information to obtain spectrum access selfishly. ML can be used to detect such actions and enhance security [16], [17]. ML also provides an optimum route to CR-VANET users to avoid traffic jams and road accidents. ML can also play a vital role in the best infotainment experience in CR-VANET. It can be used for appropriate scheduling, selecting the best channel, and prioritizing messages. CR and ML can play a major role in the next-generation driverless car system. The role of CR in the next-generation transportation system has been presented in previous discussions. This survey shows how ML can be applied to reduce road accidents and traffic congestion. CR can be used to accommodate the spectrum required to support massive data communication among automated driverless vehicles and networks. ML can be an integral part of this driverless or automated vehicle system. Similar to a robot, an autonomous vehicle (AV) can learn the surrounding environment and communicate with increased safety, reliability, QoS, and energy efficiency by applying such learning. This paper presents the dynamic usages of ML in CR-VANET elaborately. Several of the benefits of CR in VANETs and ML in VANETs and CR-VANETs are presented in Table 1. B. CONTRIBUTIONS OF THIS SURVEY ARTICLE Many survey articles describe CR, VANET, ML, and CR-VANETs individually or describe a few aspects of their amalgamation. To the best of our knowledge, surveys that cover the usage of ML in CR-VANET...

show abstract

A Reward-driven Model of Darwinian Fitness

Teichmann

Alonso

Broom

2015

Proceedings of the 7th International Joint Conference on Computational Intelligence

Self Cite

View full text Add to dashboard Cite

Abstract:In this paper we present a model that, based on the principle of total energy balance (similar to energy conservation in Physics), bridges the gap between Darwinian fitness theories and reward-driven theories of behaviour. Results show that it is possible to accommodate the reward maximization principle underlying modern approaches in behavioural reinforcement learning and traditional fitness approaches. Our framework, presented within a prey-predator model, may have important consequences in the study of behaviour.

show abstract

The application of temporal difference learning in optimal diet models

Cited by 3 publications

References 47 publications

The power of associative learning and the ontogeny of optimal behaviour

The power of associative learning and the ontogeny of optimal behaviour

Comprehensive Survey of Machine Learning Approaches in Cognitive Radio-Based Vehicular Ad Hoc Networks

A Reward-driven Model of Darwinian Fitness

Contact Info

Product

Resources

About