REPPO is an on-policy RL method that combines pathwise policy gradients with relative entropy constraints to achieve stable training and high sample efficiency without replay buffers.
In these experiments, we remove the cross-entropy loss via HL-Gauss, layer normalization, the auxiliary self-predictive loss, or the KL regularization of the policy updates
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Relative Entropy Pathwise Policy Optimization
REPPO is an on-policy RL method that combines pathwise policy gradients with relative entropy constraints to achieve stable training and high sample efficiency without replay buffers.