Frictional Q-Learning encodes supported actions as tangent directions on an action manifold using a contrastive variational autoencoder to reduce extrapolation errors in off-policy reinforcement learning.
Actor-critic algorithms
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
-
Frictional Q-Learning
Frictional Q-Learning encodes supported actions as tangent directions on an action manifold using a contrastive variational autoencoder to reduce extrapolation errors in off-policy reinforcement learning.