PAMC recovers sparse rewards via policy-weighted low-rank matrix completion and abstains when uncertain, but the provided manuscript lacks its proofs and full data.
Never give up: Learning directed exploration strategies
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?
PAMC recovers sparse rewards via policy-weighted low-rank matrix completion and abstains when uncertain, but the provided manuscript lacks its proofs and full data.