Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning

ICML, pp. 3875-3886, 2020.

Cited by: 3|Bibtex|Views55|Links
EI

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. Here we introduce Prediction of Bootstrap Latents (PBL), a...More

Code:

Data:

Your rating :
0

 

Tags
Comments