Dataset Information

Simulating bout-and-pause patterns with reinforcement learning.

ABSTRACT: Animal responses occur according to a specific temporal structure composed of two states, where a bout is followed by a long pause until the next bout. Such a bout-and-pause pattern has three components: the bout length, the within-bout response rate, and the bout initiation rate. Previous studies have investigated how these three components are affected by experimental manipulations. However, it remains unknown what underlying mechanisms cause bout-and-pause patterns. In this article, we propose two mechanisms and examine computational models developed based on reinforcement learning. The model is characterized by two mechanisms. The first mechanism is choice-an agent makes a choice between operant and other behaviors. The second mechanism is cost-a cost is associated with the changeover of behaviors. These two mechanisms are extracted from past experimental findings. Simulation results suggested that both the choice and cost mechanisms are required to generate bout-and-pause patterns and if either of them is knocked out, the model does not generate bout-and-pause patterns. We further analyzed the proposed model and found that it reproduced the relationships between experimental manipulations and the three components that have been reported by previous studies. In addition, we showed alternative models can generate bout-and-pause patterns as long as they implement the two mechanisms.

SUBMITTER: Yamada K

PROVIDER: S-EPMC7660465 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Simulating bout-and-pause patterns with reinforcement learning.

Yamada Kota K Kanemura Atsunori A

PloS one 20201112 11

Animal responses occur according to a specific temporal structure composed of two states, where a bout is followed by a long pause until the next bout. Such a bout-and-pause pattern has three components: the bout length, the within-bout response rate, and the bout initiation rate. Previous studies have investigated how these three components are affected by experimental manipulations. However, it remains unknown what underlying mechanisms cause bout-and-pause patterns. In this article, we propos ...[more]

PMID: 33180864

Similar Datasets

Project description:The study of rhythms and oscillations in the brain is gaining attention. While it is unclear exactly what the role of oscillation, synchrony, and rhythm is, it appears increasingly likely that synchrony is related to normal and abnormal brain states and possibly cognition. In this article, we explore the relationship between basal ganglia (BG) synchrony and reinforcement learning. We simulate a biologically-realistic model of the striatum initially proposed by Ponzi and Wickens (2010) and enhance the model by adding plastic cortico-BG synapses that can be modified using reinforcement learning. The effect of reinforcement learning on striatal rhythmic activity is then explored, and disrupted using simulated deep brain stimulation (DBS). The stimulator injects current in the brain structure to which it is attached, which affects neuronal synchrony. The results show that training the model without DBS yields a high accuracy in the learning task and reduced the number of active neurons in the striatum, along with an increased firing periodicity and a decreased firing synchrony between neurons in the same assembly. In addition, a spectral decomposition shows a stronger signal for correct trials than incorrect trials in high frequency bands. If the DBS is ON during the training phase, but not the test phase, the amount of learning in the model is reduced, along with firing periodicity. Similar to when the DBS is OFF, spectral decomposition shows a stronger signal for correct trials than for incorrect trials in high frequency domains, but this phenoemenon happens in higher frequency bands than when the DBS is OFF. Synchrony between the neurons is not affected. Finally, the results show that turning the DBS ON at test increases both firing periodicity and striatal synchrony, and spectral decomposition of the signal show that neural activity synchronizes with the DBS fundamental frequency (and its harmonics). Turning the DBS ON during the test phase results in chance performance regardless of whether the DBS was ON or OFF during training. We conclude that reinforcement learning is related to firing periodicity, and a stronger signal for correct trials when compared to incorrect trials in high frequency bands.

Dataset Information

Simulating bout-and-pause patterns with reinforcement learning.

Publications

Simulating bout-and-pause patterns with reinforcement learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets