PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Reinforcement learning”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 379 records · Page 21Linked to original sources
PubMed1978

[Effect of blockers of serotonin and noradrenaline synthesis on learning with emotionally different reinforcement in rats].

The effect of inhibitor of serotonin and norepinephrine synthesis in the brain on learning was investigated in rats with emotionally different reinforcement. Parachlorphenylalanine (320 mg/kg) was shown to inhibit learning with food reinforcement, but facilitated learning with pain reinforcement. Disulfiram (100 mg/kg) inhibited learning with pain reinforcement considerably, but failed to influence learning with food reinforcement. Alpha-methyl-m-thyrosine inhibited both forms of learning. These new facts are in line with our previous data on mediating role of the brain monoaminergic systems between emotions and memory.

Animals↗
PubMed1981

[Effects of bilateral mammillary bodies destruction on lever pressing for food reward in the rabbit (author's transl)].

Effects for continuous reinforcement (CRF) learning and differential reinforcement of low rate (DRL) learning for food in the rabbit by bilateral mammillary bodies destruction were examined with the Skinner box. There was no marked changes in general behavior, except a tendency to freezing by a sign of somebody and sounds. In CRF learning a delay in the start of bar pressing was thought to be due to a decrease in exploratory behavior and a decrease of the number of bar pressing may be due either to a delay of adaptation to a new environment, or to an impediment of learning by the decrease in rewarding effects. The acquisition of DRL learning was affected, but the retention of that was not. DRL learning has been generally remarked to be chiefly consisted of motivation and temporal discrimination. In our study, however, there was no remarkable changes in motivation itself and temporal discrimination was not affected at all. It was concluded that the impediment of acquisition depended upon a general decrease in cerebral rewarding effects.

Animals↗
PubMed2004

Combining expert neural networks using reinforcement feedback for learning primitive grasping behavior.

This paper present an architecture for combining a mixture of experts. The architecture has two unique features: 1) it assumes no prior knowledge of the size or structure of the mixture and allows the number of experts to dynamically expand during training, and 2) reinforcement feedback is used to guide the combining/expansion operation. The architecture is particularly suitable for applications when there is a need to approximate a many-to-many mapping. An example of such a problem is the task of training a robot to grasp arbitrarily shaped objects. This task requires the approximation of a many-to-many mapping, since various configurations can be used to grasp an object, and several objects can share the same grasping configuration. Experiments in a simulated environment using a 28-object database showed how the algorithm dynamically combined and expanded a mixture of neural networks to achieve the learning task. The paper also presents a comparison with two other nonlearning approaches.

Feedback↗
PubMed1997

The tuberomammillary nucleus projections in the control of learning, memory and reinforcement processes: evidence for an inhibitory role.

The tuberomammillary nucleus (TM), a cluster of magnocellular cells in the posterior hypothalamus, is the main source of neuronal histamine in the brain. Although this nucleus is well described in terms of anatomy and neurochemistry, only little is known about its function. Our earlier work showed that the TM projection system may be involved in behavioral asymmetries and behavioral recovery after unilateral manipulations of the brain. Using horseradish peroxidase (HRP) labeling we found an increase in strength (structure and/or activity) in the crossed and uncrossed tuberomammillary-striatal projections in the course of recovery from behavioral asymmetries produced by unilateral removal of the rats' vibrissae, which were in the same direction as the asymmetries found in projections from the substantia nigra to the striatum. Experiments performed with unilateral lesions of the TM region provide evidence for an involvement of the TM system in reinforcement mechanisms. Unilateral destruction of the TM with direct current (DC) or ibotenic acid was found to increase the rate of lateral hypothalamic self-stimulation ipsilateral to the lesion site, suggesting that the TM (particularly the E2 subgroup in its rostral part) may function as a reinforcement inhibiting neural substrate. Experiments performed with bilateral DC or ibotenic acid lesions of the TM region suggest a role of the nucleus in learning and mnemonic processes. A bilateral electrolytic or neurotoxic lesion of the TM region was found to facilitate the performance of adult and behaviorally impaired aged rats in a variety of learning tasks, including a habituation paradigm, aversively motivated learning tasks and water mazes. Examination of the site of the neurotoxic lesion in the TM region with immunohistochemical techniques revealed a marked decline of histamine-staining neurons mainly in the rostral part of the TM nucleus, suggesting that the facilitatory effects on reinforcement and mnemonic processes might be related to the destruction of TM intrinsic histaminergic cells. In summary, the present results indicate that the TM nucleus is involved in neural plasticity and functional recovery following damage to the CNS and may function as an inhibitory neural substrate in the control of reinforcement and mnemonic processes.

Animals↗
PubMed2003

The role of perirhinal cortex in visual discrimination learning for visual secondary reinforcement in rats.

Perirhinal cortex in monkeys has been thought to be involved in visual associative learning. The authors examined rats' ability to make associations between visual stimuli in a visual secondary reinforcement task. Rats learned 2-choice visual discriminations for secondary visual reinforcement. They showed significant learning of discriminations before any primary reinforcement. Following bilateral perirhinal cortex lesions, rats continued to learn visual discriminations for visual secondary reinforcement at the same rate as before surgery. Thus, this study does not support a critical role of perirhinal cortex in learning for visual secondary reinforcement. Contrasting this result with other positive results, the authors suggest that the role of perirhinal cortex is in "within-object" associations and that it plays a much lesser role in stimulus-stimulus associations between objects.

Animals↗