A new marginalized reparameterization estimator allows low-variance training of mixture policies in entropy-regularized actor-critic algorithms, matching or exceeding Gaussian policy performance in several continuous control benchmarks.
Leveraging exploration in off-policy algorithms via normalizing flows
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
-
Revisiting Mixture Policies in Entropy-Regularized Actor-Critic
A new marginalized reparameterization estimator allows low-variance training of mixture policies in entropy-regularized actor-critic algorithms, matching or exceeding Gaussian policy performance in several continuous control benchmarks.