Bayesian modeling of policy gradients as Gaussian processes and actor-critic variants reduce sample needs and provide uncertainty estimates compared to Monte-Carlo methods.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bayesian policy gradient and actor-critic algorithms
Bayesian modeling of policy gradients as Gaussian processes and actor-critic variants reduce sample needs and provide uncertainty estimates compared to Monte-Carlo methods.