Cargando…
Maximum Entropy Exploration in Contextual Bandits with Neural Networks and Energy Based Models
Contextual bandits can solve a huge range of real-world problems. However, current popular algorithms to solve them either rely on linear models or unreliable uncertainty estimation in non-linear models, which are required to deal with the exploration–exploitation trade-off. Inspired by theories of...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9955972/ https://www.ncbi.nlm.nih.gov/pubmed/36832555 http://dx.doi.org/10.3390/e25020188 |
_version_ | 1784894478238089216 |
---|---|
author | Elwood, Adam Leonardi, Marco Mohamed, Ashraf Rozza, Alessandro |
author_facet | Elwood, Adam Leonardi, Marco Mohamed, Ashraf Rozza, Alessandro |
author_sort | Elwood, Adam |
collection | PubMed |
description | Contextual bandits can solve a huge range of real-world problems. However, current popular algorithms to solve them either rely on linear models or unreliable uncertainty estimation in non-linear models, which are required to deal with the exploration–exploitation trade-off. Inspired by theories of human cognition, we introduce novel techniques that use maximum entropy exploration, relying on neural networks to find optimal policies in settings with both continuous and discrete action spaces. We present two classes of models, one with neural networks as reward estimators, and the other with energy based models, which model the probability of obtaining an optimal reward given an action. We evaluate the performance of these models in static and dynamic contextual bandit simulation environments. We show that both techniques outperform standard baseline algorithms, such as NN HMC, NN Discrete, Upper Confidence Bound, and Thompson Sampling, where energy based models have the best overall performance. This provides practitioners with new techniques that perform well in static and dynamic settings, and are particularly well suited to non-linear scenarios with continuous action spaces. |
format | Online Article Text |
id | pubmed-9955972 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-99559722023-02-25 Maximum Entropy Exploration in Contextual Bandits with Neural Networks and Energy Based Models Elwood, Adam Leonardi, Marco Mohamed, Ashraf Rozza, Alessandro Entropy (Basel) Article Contextual bandits can solve a huge range of real-world problems. However, current popular algorithms to solve them either rely on linear models or unreliable uncertainty estimation in non-linear models, which are required to deal with the exploration–exploitation trade-off. Inspired by theories of human cognition, we introduce novel techniques that use maximum entropy exploration, relying on neural networks to find optimal policies in settings with both continuous and discrete action spaces. We present two classes of models, one with neural networks as reward estimators, and the other with energy based models, which model the probability of obtaining an optimal reward given an action. We evaluate the performance of these models in static and dynamic contextual bandit simulation environments. We show that both techniques outperform standard baseline algorithms, such as NN HMC, NN Discrete, Upper Confidence Bound, and Thompson Sampling, where energy based models have the best overall performance. This provides practitioners with new techniques that perform well in static and dynamic settings, and are particularly well suited to non-linear scenarios with continuous action spaces. MDPI 2023-01-18 /pmc/articles/PMC9955972/ /pubmed/36832555 http://dx.doi.org/10.3390/e25020188 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Elwood, Adam Leonardi, Marco Mohamed, Ashraf Rozza, Alessandro Maximum Entropy Exploration in Contextual Bandits with Neural Networks and Energy Based Models |
title | Maximum Entropy Exploration in Contextual Bandits with Neural Networks and Energy Based Models |
title_full | Maximum Entropy Exploration in Contextual Bandits with Neural Networks and Energy Based Models |
title_fullStr | Maximum Entropy Exploration in Contextual Bandits with Neural Networks and Energy Based Models |
title_full_unstemmed | Maximum Entropy Exploration in Contextual Bandits with Neural Networks and Energy Based Models |
title_short | Maximum Entropy Exploration in Contextual Bandits with Neural Networks and Energy Based Models |
title_sort | maximum entropy exploration in contextual bandits with neural networks and energy based models |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9955972/ https://www.ncbi.nlm.nih.gov/pubmed/36832555 http://dx.doi.org/10.3390/e25020188 |
work_keys_str_mv | AT elwoodadam maximumentropyexplorationincontextualbanditswithneuralnetworksandenergybasedmodels AT leonardimarco maximumentropyexplorationincontextualbanditswithneuralnetworksandenergybasedmodels AT mohamedashraf maximumentropyexplorationincontextualbanditswithneuralnetworksandenergybasedmodels AT rozzaalessandro maximumentropyexplorationincontextualbanditswithneuralnetworksandenergybasedmodels |