pith. sign in

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 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Relative Entropy Pathwise Policy Optimization

cs.LG · 2025-07-15 · unverdicted · novelty 5.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Relative Entropy Pathwise Policy Optimization cs.LG · 2025-07-15 · unverdicted · none · ref 18

    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.