Cargando…
Learning to play against any mixture of opponents
Intuitively, experience playing against one mixture of opponents in a given domain should be relevant for a different mixture in the same domain. If the mixture changes, ideally we would not have to train from scratch, but rather could transfer what we have learned to construct a policy to play agai...
Autores principales: | Smith, Max Olan, Anthony, Thomas, Wellman, Michael P. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10400709/ https://www.ncbi.nlm.nih.gov/pubmed/37547229 http://dx.doi.org/10.3389/frai.2023.804682 |
Ejemplares similares
-
Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data
por: Czech, Johannes, et al.
Publicado: (2020) -
Unsupervised Quark/Gluon Jet Tagging With Poissonian Mixture Models
por: Alvarez, E., et al.
Publicado: (2022) -
The Applicability of Self-Play Algorithms to Trading and Forecasting Financial Markets
por: Posth, Jan-Alexander, et al.
Publicado: (2021) -
Artificial intelligence for analyzing orthopedic trauma radiographs: Deep learning algorithms—are they on par with humans for diagnosing fractures?
por: Olczak, Jakub, et al.
Publicado: (2017) -
Benefits of Adaptive Learning Transfer From Typing-Based Learning to Speech-Based Learning
por: Wilschut, Thomas, et al.
Publicado: (2021)