載入...

Human Reinforcement Learning Subdivides Structured Action Spaces by Learning Effector-Specific Values

Humans and animals are endowed with a large number of effectors. Although this enables great behavioral flexibility, it presents an equally formidable reinforcement learning problem of discovering which actions are most valuable because of the high dimensionality of the action space. An unresolved q...

全面介紹

Na minha lista:
書目詳細資料
Main Authors: Gershman, Samuel J., Pesaran, Bijan, Daw, Nathaniel D.
格式: Artigo
語言:Inglês
出版: Society for Neuroscience 2009
主題:
在線閱讀:https://ncbi.nlm.nih.gov/pmc/articles/PMC2796632/
https://ncbi.nlm.nih.gov/pubmed/19864565
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1523/JNEUROSCI.2469-09.2009
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!