AISAC extends actor-critic methods by actively optimizing the data-collection policy via importance sampling and cross-entropy minimization to lower gradient variance and improve learning in continuous action spaces.
Sutton and David A
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
-
Actor-Critic with Active Importance Sampling
AISAC extends actor-critic methods by actively optimizing the data-collection policy via importance sampling and cross-entropy minimization to lower gradient variance and improve learning in continuous action spaces.