A model combining distributional successor features with successor representations supports RL in noisy partially observable environments.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A neurally plausible model learns successor representations in partially observable environments
A model combining distributional successor features with successor representations supports RL in noisy partially observable environments.