Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning

doi:doi:10.57702/y012ybb5

Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning

Learning a good representation is an essential component for deep reinforcement learning (RL). Representation learning is especially important in multitask and partially observable settings where building a representation of the unknown environment is crucial to solve the tasks.

BibTex:

@dataset{Daniel_Guo_and_Bernardo_Avila_Pires_and_Bilal_Piot_and_Jean_Bastien_Grill_and_Florent_Altché_and_Rémi_Munos_and_Mohammad_Gheshlaghi_Azar_2024,
    abstract = {Learning a good representation is an essential component for deep reinforcement learning (RL). Representation learning is especially important in multitask and partially observable settings where building a representation of the unknown environment is crucial to solve the tasks.},
    author = {Daniel Guo and Bernardo Avila Pires and Bilal Piot and Jean Bastien Grill and Florent Altché and Rémi Munos and Mohammad Gheshlaghi Azar},
    doi = {10.57702/y012ybb5},
    institution = {No Organization},
    keyword = {'Multitask Reinforcement Learning', 'Partially Observable Environments', 'Representation Learning'},
    month = {dec},
    publisher = {TIB},
    title = {Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning},
    url = {https://service.tib.eu/ldmservice/dataset/bootstrap-latent-predictive-representations-for-multitask-reinforcement-learning},
    year = {2024}
}