Dynamic-depth context tree weighting

Reinforcement learning (RL) in partially observable settings is challenging be- cause the agent’s immediate observations are not Markov. Recently proposed methods can learn variable-order Markov models of the underlying process but have steep memory requirements and are sensitive to aliasing betw...

Descripción completa

Detalles Bibliográficos
Autores principales: Messias, J, Whiteson, S
Formato: Conference item
Publicado: Curran Associates 2018