CrossQ with weight normalization scales to high update-to-data ratios and matches or outperforms reset-based baselines on 25 continuous control benchmarks.
Randomized ensembled double Q- learning: Learning fast without a model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization
CrossQ with weight normalization scales to high update-to-data ratios and matches or outperforms reset-based baselines on 25 continuous control benchmarks.