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.

Data and Resources

Cite this as

Daniel Guo, Bernardo Avila Pires, Bilal Piot, Jean Bastien Grill, Florent Altché, Rémi Munos, Mohammad Gheshlaghi Azar (2024). Dataset: Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning. https://doi.org/10.57702/y012ybb5

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2004.14646
Author Daniel Guo
More Authors
Bernardo Avila Pires
Bilal Piot
Jean Bastien Grill
Florent Altché
Rémi Munos
Mohammad Gheshlaghi Azar