AdamO modifies Adam with an orthogonality correction to ensure the spectral radius of the TD update operator stays below one, providing a theoretical stability guarantee for offline RL.
arXiv preprint arXiv:2211.11092 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AdamO: A Collapse-Suppressed Optimizer for Offline RL
AdamO modifies Adam with an orthogonality correction to ensure the spectral radius of the TD update operator stays below one, providing a theoretical stability guarantee for offline RL.