Skip to content
conftrace_

kl-divergence constraint

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

model-free algorithm (1) q-function approximation (1) continual setting (1) k-fac approximation (1) replay data (1) action entropy regularization (1) policy update (1) layer normalization (1) model-free reinforcement learning (1) second-order information (1)

Papers

Online Curvature-Aware Replay: Leveraging $\mathbf2^nd$ Order Information for Online Continual Learning ICML 2025 Test-time Adapted Reinforcement Learning with Action Entropy Regularization ICML 2025 Model-Free Trajectory Optimization for Reinforcement Learning ICML 2016