Introducing neuromodulation in deep neural networks to learn adaptive behaviours.
Animals excel at adapting their intentions, attention, and actions to the environment, making them remarkably efficient at interacting with a rich, unpredictable and ever-changing external world, a property that intelligent machines currently lack. Such an adaptation property relies heavily on cellu...
Saved in:
| _version_ | 1850205672523694080 |
|---|---|
| author | Nicolas Vecoven Damien Ernst Antoine Wehenkel Guillaume Drion |
| author_facet | Nicolas Vecoven Damien Ernst Antoine Wehenkel Guillaume Drion |
| author_sort | Nicolas Vecoven |
| collection | DOAJ |
| description | Animals excel at adapting their intentions, attention, and actions to the environment, making them remarkably efficient at interacting with a rich, unpredictable and ever-changing external world, a property that intelligent machines currently lack. Such an adaptation property relies heavily on cellular neuromodulation, the biological mechanism that dynamically controls intrinsic properties of neurons and their response to external stimuli in a context-dependent manner. In this paper, we take inspiration from cellular neuromodulation to construct a new deep neural network architecture that is specifically designed to learn adaptive behaviours. The network adaptation capabilities are tested on navigation benchmarks in a meta-reinforcement learning context and compared with state-of-the-art approaches. Results show that neuromodulation is capable of adapting an agent to different tasks and that neuromodulation-based approaches provide a promising way of improving adaptation of artificial systems. |
| format | Article |
| id | doaj-art-e2010d89f7ec4aefb63cdb6ae520fcaa |
| institution | OA Journals |
| issn | 1932-6203 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-e2010d89f7ec4aefb63cdb6ae520fcaa2025-08-20T02:11:01ZengPublic Library of Science (PLoS)PLoS ONE1932-62032020-01-01151e022792210.1371/journal.pone.0227922Introducing neuromodulation in deep neural networks to learn adaptive behaviours.Nicolas VecovenDamien ErnstAntoine WehenkelGuillaume DrionAnimals excel at adapting their intentions, attention, and actions to the environment, making them remarkably efficient at interacting with a rich, unpredictable and ever-changing external world, a property that intelligent machines currently lack. Such an adaptation property relies heavily on cellular neuromodulation, the biological mechanism that dynamically controls intrinsic properties of neurons and their response to external stimuli in a context-dependent manner. In this paper, we take inspiration from cellular neuromodulation to construct a new deep neural network architecture that is specifically designed to learn adaptive behaviours. The network adaptation capabilities are tested on navigation benchmarks in a meta-reinforcement learning context and compared with state-of-the-art approaches. Results show that neuromodulation is capable of adapting an agent to different tasks and that neuromodulation-based approaches provide a promising way of improving adaptation of artificial systems.https://storage.googleapis.com/plos-corpus-prod/10.1371/journal.pone.0227922/1/pone.0227922.pdf?X-Goog-Algorithm=GOOG4-RSA-SHA256&X-Goog-Credential=wombat-sa%40plos-prod.iam.gserviceaccount.com%2F20210219%2Fauto%2Fstorage%2Fgoog4_request&X-Goog-Date=20210219T120936Z&X-Goog-Expires=3600&X-Goog-SignedHeaders=host&X-Goog-Signature=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 |
| spellingShingle | Nicolas Vecoven Damien Ernst Antoine Wehenkel Guillaume Drion Introducing neuromodulation in deep neural networks to learn adaptive behaviours. PLoS ONE |
| title | Introducing neuromodulation in deep neural networks to learn adaptive behaviours. |
| title_full | Introducing neuromodulation in deep neural networks to learn adaptive behaviours. |
| title_fullStr | Introducing neuromodulation in deep neural networks to learn adaptive behaviours. |
| title_full_unstemmed | Introducing neuromodulation in deep neural networks to learn adaptive behaviours. |
| title_short | Introducing neuromodulation in deep neural networks to learn adaptive behaviours. |
| title_sort | introducing neuromodulation in deep neural networks to learn adaptive behaviours |
| url | https://storage.googleapis.com/plos-corpus-prod/10.1371/journal.pone.0227922/1/pone.0227922.pdf?X-Goog-Algorithm=GOOG4-RSA-SHA256&X-Goog-Credential=wombat-sa%40plos-prod.iam.gserviceaccount.com%2F20210219%2Fauto%2Fstorage%2Fgoog4_request&X-Goog-Date=20210219T120936Z&X-Goog-Expires=3600&X-Goog-SignedHeaders=host&X-Goog-Signature=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 |
| work_keys_str_mv | AT nicolasvecoven introducingneuromodulationindeepneuralnetworkstolearnadaptivebehaviours AT damienernst introducingneuromodulationindeepneuralnetworkstolearnadaptivebehaviours AT antoinewehenkel introducingneuromodulationindeepneuralnetworkstolearnadaptivebehaviours AT guillaumedrion introducingneuromodulationindeepneuralnetworkstolearnadaptivebehaviours |