ABPT averages a zero-step value gradient with an N-step backpropagation gradient so that non-differentiable reward components do not fully block policy learning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ABPT: Amended Backpropagation through Time with Partially Differentiable Rewards
ABPT averages a zero-step value gradient with an N-step backpropagation gradient so that non-differentiable reward components do not fully block policy learning.